Publications

@misc{jalal-kamali_predicting_2025,

title = {Predicting Team Performance from Communications in Simulated Search-and-Rescue},

author = {Ali Jalal-Kamali and Nikolos Gurney and David Pynadath},

url = {http://arxiv.org/abs/2503.03791},

doi = {10.48550/arXiv.2503.03791},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-18},

publisher = {arXiv},

abstract = {Understanding how individual traits influence team performance is valuable, but these traits are not always directly observable. Prior research has inferred traits like trust from behavioral data. We analyze conversational data to identify team traits and their correlation with teaming outcomes. Using transcripts from a Minecraft-based search-and-rescue experiment, we apply topic modeling and clustering to uncover key interaction patterns. Our findings show that variations in teaming outcomes can be explained through these inferences, with different levels of predictive power derived from individual traits and team dynamics.},

note = {arXiv:2503.03791 [cs]},

keywords = {AI, DTIC},

pubstate = {published},

tppubtype = {misc}

}

@misc{kwon_astra_2025,

title = {ASTRA: A Negotiation Agent with Adaptive and Strategic Reasoning through Action in Dynamic Offer Optimization},

author = {Deuksin Kwon and Jiwon Hae and Emma Clift and Daniel Shamsoddini and Jonathan Gratch and Gale M. Lucas},

url = {http://arxiv.org/abs/2503.07129},

doi = {10.48550/arXiv.2503.07129},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-18},

publisher = {arXiv},

abstract = {Negotiation requires dynamically balancing self-interest and cooperation to maximize one's own utility. Yet, existing agents struggle due to bounded rationality in human data, low adaptability to counterpart behavior, and limited strategic reasoning. To address this, we introduce principle-driven negotiation agents, powered by ASTRA, a novel framework for turn-level offer optimization grounded in two core principles: opponent modeling and Tit-for-Tat reciprocity. ASTRA operates in three stages: (1) interpreting counterpart behavior, (2) optimizing counteroffers via a linear programming (LP) solver, and (3) selecting offers based on negotiation tactics and the partner's acceptance probability. Through simulations and human evaluations, our agent effectively adapts to an opponent's shifting stance and achieves favorable outcomes through enhanced adaptability and strategic reasoning. Beyond improving negotiation performance, it also serves as a powerful coaching tool, offering interpretable strategic feedback and optimal offer recommendations.},

note = {arXiv:2503.07129 [cs]},

keywords = {Virtual Agents},

pubstate = {published},

tppubtype = {misc}

}

@misc{jin_promptgar_2025,

title = {PromptGAR: Flexible Promptive Group Activity Recognition},

author = {Zhangyu Jin and Andrew Feng and Ankur Chemburkar and Celso M. De Melo},

url = {http://arxiv.org/abs/2503.08933},

doi = {10.48550/arXiv.2503.08933},

year  = {2025},

date = {2025-03-01},

urldate = {2025-03-20},

publisher = {arXiv},

abstract = {We present PromptGAR, a novel framework that addresses the limitations of current Group Activity Recognition (GAR) approaches by leveraging multi-modal prompts to achieve both input flexibility and high recognition accuracy. The existing approaches suffer from limited real-world applicability due to their reliance on full prompt annotations, the lack of long-term actor consistency, and under-exploration of multi-group scenarios. To bridge the gap, we proposed PromptGAR, which is the first GAR model to provide input flexibility across prompts, frames, and instances without the need for retraining. Specifically, we unify bounding boxes, skeletal keypoints, and areas as point prompts and employ a recognition decoder for cross-updating class and prompt tokens. To ensure long-term consistency for extended activity durations, we also introduce a relative instance attention mechanism that directly encodes instance IDs. Finally, PromptGAR explores the use of area prompts to enable the selective recognition of the particular group activity within videos that contain multiple concurrent groups. Comprehensive evaluations demonstrate that PromptGAR achieves competitive performances both on full prompts and diverse prompt inputs, establishing its effectiveness on input flexibility and generalization ability for real-world applications.},

note = {arXiv:2503.08933 [cs]},

keywords = {Computer Science - Computer Vision and Pattern Recognition},

pubstate = {published},

tppubtype = {misc}

}

@misc{liu_investigating_2025,

title = {Investigating Role of Personal Factors in Shaping Responses to Active Shooter Incident using Machine Learning},

author = {Ruying Liu and Burçin Becerik-Gerber and Gale M. Lucas},

url = {http://arxiv.org/abs/2503.05719},

doi = {10.48550/arXiv.2503.05719},

year  = {2025},

date = {2025-02-01},

urldate = {2025-03-18},

publisher = {arXiv},

abstract = {This study bridges the knowledge gap on how personal factors affect building occupants' responses in active shooter situations by applying interpretable machine learning methods to data from 107 participants. The personal factors studied are training methods, prior training experience, sense of direction, and gender. The response performance measurements consist of decisions (run, hide, multiple), vulnerability (corresponding to the time a participant is visible to a shooter), and pre-evacuation time. The results indicate that the propensity to run significantly determines overall response strategies, overshadowing vulnerability, and pre-evacuation time. The training method is a critical factor where VR-based training leads to better responses than video-based training. A better sense of direction and previous training experience are correlated with a greater propensity to run and less vulnerability. Gender slightly influences decisions and vulnerability but significantly impacts pre-evacuation time, with females evacuating slower, potentially due to higher risk perception. This study underscores the importance of personal factors in shaping responses to active shooter incidents.},

note = {arXiv:2503.05719 [cs]},

keywords = {DTIC, Social Simulation, VR},

pubstate = {published},

tppubtype = {misc}

}

@misc{huang_sc-omnigs_2025,

title = {SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting},

author = {Huajian Huang and Yingshu Chen and Longwei Li and Hui Cheng and Tristan Braud and Yajie Zhao and Sai-Kit Yeung},

url = {http://arxiv.org/abs/2502.04734},

doi = {10.48550/arXiv.2502.04734},

year  = {2025},

date = {2025-02-01},

urldate = {2025-03-18},

publisher = {arXiv},

abstract = {360-degree cameras streamline data collection for radiance field 3D reconstruction by capturing comprehensive scene data. However, traditional radiance field methods do not address the specific challenges inherent to 360-degree images. We present SC-OmniGS, a novel self-calibrating omnidirectional Gaussian splatting system for fast and accurate omnidirectional radiance field reconstruction using 360-degree images. Rather than converting 360-degree images to cube maps and performing perspective image calibration, we treat 360-degree images as a whole sphere and derive a mathematical framework that enables direct omnidirectional camera pose calibration accompanied by 3D Gaussians optimization. Furthermore, we introduce a differentiable omnidirectional camera model in order to rectify the distortion of real-world data for performance enhancement. Overall, the omnidirectional camera intrinsic model, extrinsic poses, and 3D Gaussians are jointly optimized by minimizing weighted spherical photometric loss. Extensive experiments have demonstrated that our proposed SC-OmniGS is able to recover a high-quality radiance field from noisy camera poses or even no pose prior in challenging scenarios characterized by wide baselines and non-object-centric configurations. The noticeable performance gain in the real-world dataset captured by consumer-grade omnidirectional cameras verifies the effectiveness of our general omnidirectional camera model in reducing the distortion of 360-degree images.},

note = {arXiv:2502.04734 [cs]},

keywords = {},

pubstate = {published},

tppubtype = {misc}

}

@misc{tak_mechanistic_2025,

title = {Mechanistic Interpretability of Emotion Inference in Large Language Models},

author = {Ala N. Tak and Amin Banayeeanzade and Anahita Bolourani and Mina Kian and Robin Jia and Jonathan Gratch},

url = {http://arxiv.org/abs/2502.05489},

doi = {10.48550/arXiv.2502.05489},

year  = {2025},

date = {2025-02-01},

urldate = {2025-02-20},

publisher = {arXiv},

abstract = {Large language models (LLMs) show promising capabilities in predicting human emotions from text. However, the mechanisms through which these models process emotional stimuli remain largely unexplored. Our study addresses this gap by investigating how autoregressive LLMs infer emotions, showing that emotion representations are functionally localized to specific regions in the model. Our evaluation includes diverse model families and sizes and is supported by robustness checks. We then show that the identified representations are psychologically plausible by drawing on cognitive appraisal theory, a well-established psychological framework positing that emotions emerge from evaluations (appraisals) of environmental stimuli. By causally intervening on construed appraisal concepts, we steer the generation and show that the outputs align with theoretical and intuitive expectations. This work highlights a novel way to causally intervene and precisely shape emotional text generation, potentially benefiting safety and alignment in sensitive affective domains.},

note = {arXiv:2502.05489 [cs]},

keywords = {},

pubstate = {published},

tppubtype = {misc}

}

@misc{brun_exploring_2025,

title = {Exploring Emotion-Sensitive LLM-Based Conversational AI},

author = {Antonin Brun and Ruying Liu and Aryan Shukla and Frances Watson and Jonathan Gratch},

url = {http://arxiv.org/abs/2502.08920},

doi = {10.48550/arXiv.2502.08920},

year  = {2025},

date = {2025-02-01},

urldate = {2025-02-20},

publisher = {arXiv},

abstract = {Conversational AI chatbots have become increasingly common within the customer service industry. Despite improvements in their emotional development, they often lack the authenticity of real customer service interactions or the competence of service providers. By comparing emotion-sensitive and emotion-insensitive LLM-based chatbots across 30 participants, we aim to explore how emotional sensitivity in chatbots influences perceived competence and overall customer satisfaction in service interactions. Additionally, we employ sentiment analysis techniques to analyze and interpret the emotional content of user inputs. We highlight that perceptions of chatbot trustworthiness and competence were higher in the case of the emotion-sensitive chatbot, even if issue resolution rates were not affected. We discuss implications of improved user satisfaction from emotion-sensitive chatbots and potential applications in support services.},

note = {arXiv:2502.08920 [cs]},

keywords = {AI, LLM},

pubstate = {published},

tppubtype = {misc}

}

@misc{hu_splatmap_2025,

title = {SplatMAP: Online Dense Monocular SLAM with 3D Gaussian Splatting},

author = {Yue Hu and Rong Liu and Meida Chen and Peter Beerel and Andrew Feng},

url = {http://arxiv.org/abs/2501.07015},

doi = {10.48550/arXiv.2501.07015},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-16},

publisher = {arXiv},

abstract = {Achieving high-fidelity 3D reconstruction from monocular video remains challenging due to the inherent limitations of traditional methods like Structure-from-Motion (SfM) and monocular SLAM in accurately capturing scene details. While differentiable rendering techniques such as Neural Radiance Fields (NeRF) address some of these challenges, their high computational costs make them unsuitable for real-time applications. Additionally, existing 3D Gaussian Splatting (3DGS) methods often focus on photometric consistency, neglecting geometric accuracy and failing to exploit SLAM's dynamic depth and pose updates for scene refinement. We propose a framework integrating dense SLAM with 3DGS for real-time, high-fidelity dense reconstruction. Our approach introduces SLAM-Informed Adaptive Densification, which dynamically updates and densifies the Gaussian model by leveraging dense point clouds from SLAM. Additionally, we incorporate Geometry-Guided Optimization, which combines edge-aware geometric constraints and photometric consistency to jointly optimize the appearance and geometry of the 3DGS scene representation, enabling detailed and accurate SLAM mapping reconstruction. Experiments on the Replica and TUM-RGBD datasets demonstrate the effectiveness of our approach, achieving state-of-the-art results among monocular systems. Specifically, our method achieves a PSNR of 36.864, SSIM of 0.985, and LPIPS of 0.040 on Replica, representing improvements of 10.7%, 6.4%, and 49.4%, respectively, over the previous SOTA. On TUM-RGBD, our method outperforms the closest baseline by 10.2%, 6.6%, and 34.7% in the same metrics. These results highlight the potential of our framework in bridging the gap between photometric and geometric dense 3D scene representations, paving the way for practical and efficient monocular dense reconstruction.},

note = {arXiv:2501.07015 [cs]},

keywords = {VGL},

pubstate = {published},

tppubtype = {misc}

}

@misc{liu_deformable_2025,

title = {Deformable Beta Splatting},

author = {Rong Liu and Dylan Sun and Meida Chen and Yue Wang and Andrew Feng},

url = {http://arxiv.org/abs/2501.18630},

doi = {10.48550/arXiv.2501.18630},

year  = {2025},

date = {2025-01-01},

urldate = {2025-02-20},

publisher = {arXiv},

abstract = {3D Gaussian Splatting (3DGS) has advanced radiance field reconstruction by enabling real-time rendering. However, its reliance on Gaussian kernels for geometry and low-order Spherical Harmonics (SH) for color encoding limits its ability to capture complex geometries and diverse colors. We introduce Deformable Beta Splatting (DBS), a deformable and compact approach that enhances both geometry and color representation. DBS replaces Gaussian kernels with deformable Beta Kernels, which offer bounded support and adaptive frequency control to capture fine geometric details with higher fidelity while achieving better memory efficiency. In addition, we extended the Beta Kernel to color encoding, which facilitates improved representation of diffuse and specular components, yielding superior results compared to SH-based methods. Furthermore, Unlike prior densification techniques that depend on Gaussian properties, we mathematically prove that adjusting regularized opacity alone ensures distribution-preserved Markov chain Monte Carlo (MCMC), independent of the splatting kernel type. Experimental results demonstrate that DBS achieves state-of-the-art visual quality while utilizing only 45% of the parameters and rendering 1.5x faster than 3DGS-based methods. Notably, for the first time, splatting-based methods outperform state-of-the-art Neural Radiance Fields, highlighting the superior performance and efficiency of DBS for real-time radiance field rendering.},

note = {arXiv:2501.18630 [cs]},

keywords = {DTIC, Narrative},

pubstate = {published},

tppubtype = {misc}

}

@misc{chang_x-dyna_2025,

title = {X-Dyna: Expressive Dynamic Human Image Animation},

author = {Di Chang and Hongyi Xu and You Xie and Yipeng Gao and Zhengfei Kuang and Shengqu Cai and Chenxu Zhang and Guoxian Song and Chao Wang and Yichun Shi and Zeyuan Chen and Shijie Zhou and Linjie Luo and Gordon Wetzstein and Mohammad Soleymani},

url = {http://arxiv.org/abs/2501.10021},

doi = {10.48550/arXiv.2501.10021},

year  = {2025},

date = {2025-01-01},

urldate = {2025-02-20},

publisher = {arXiv},

abstract = {We introduce X-Dyna, a novel zero-shot, diffusion-based pipeline for animating a single human image using facial expressions and body movements derived from a driving video, that generates realistic, context-aware dynamics for both the subject and the surrounding environment. Building on prior approaches centered on human pose control, X-Dyna addresses key shortcomings causing the loss of dynamic details, enhancing the lifelike qualities of human video animations. At the core of our approach is the Dynamics-Adapter, a lightweight module that effectively integrates reference appearance context into the spatial attentions of the diffusion backbone while preserving the capacity of motion modules in synthesizing fluid and intricate dynamic details. Beyond body pose control, we connect a local control module with our model to capture identity-disentangled facial expressions, facilitating accurate expression transfer for enhanced realism in animated scenes. Together, these components form a unified framework capable of learning physical human motion and natural scene dynamics from a diverse blend of human and scene videos. Comprehensive qualitative and quantitative evaluations demonstrate that X-Dyna outperforms state-of-the-art methods, creating highly lifelike and expressive animations. The code is available at https://github.com/bytedance/X-Dyna.},

note = {arXiv:2501.10021 [cs]},

keywords = {VGL},

pubstate = {published},

tppubtype = {misc}

}

@misc{siniukov_towards_2025,

title = {Towards a Generalizable Speech Marker for Parkinson's Disease Diagnosis},

author = {Maksim Siniukov and Ellie Xing and Sanaz and Attaripour Isfahani and Mohammad Soleymani},

url = {https://arxiv.org/abs/2501.03581},

doi = {10.48550/ARXIV.2501.03581},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-14},

publisher = {arXiv},

abstract = {Parkinson's Disease (PD) is a neurodegenerative disorder characterized by motor symptoms, including altered voice production in the early stages. Early diagnosis is crucial not only to improve PD patients' quality of life but also to enhance the efficacy of potential disease-modifying therapies during early neurodegeneration, a window often missed by current diagnostic tools. In this paper, we propose a more generalizable approach to PD recognition through domain adaptation and self-supervised learning. We demonstrate the generalization capabilities of the proposed approach across diverse datasets in different languages. Our approach leverages HuBERT, a large deep neural network originally trained for speech recognition and further trains it on unlabeled speech data from a population that is similar to the target group, i.e., the elderly, in a self-supervised manner. The model is then fine-tuned and adapted for use across different datasets in multiple languages, including English, Italian, and Spanish. Evaluations on four publicly available PD datasets demonstrate the model's efficacy, achieving an average specificity of 92.1% and an average sensitivity of 91.2%. This method offers objective and consistent evaluations across large populations, addressing the variability inherent in human assessments and providing a non-invasive, cost-effective and accessible diagnostic option.},

note = {Version Number: 1},

keywords = {DTIC},

pubstate = {published},

tppubtype = {misc}

}

@misc{addison_c-fedrag_2024,

title = {C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System},

author = {Parker Addison and Minh-Tuan H. Nguyen and Tomislav Medan and Jinali Shah and Mohammad T. Manzari and Brendan McElrone and Laksh Lalwani and Aboli More and Smita Sharma and Holger R. Roth and Isaac Yang and Chester Chen and Daguang Xu and Yan Cheng and Andrew Feng and Ziyue Xu},

url = {http://arxiv.org/abs/2412.13163},

doi = {10.48550/arXiv.2412.13163},

year  = {2024},

date = {2024-12-01},

urldate = {2025-03-20},

publisher = {arXiv},

abstract = {Organizations seeking to utilize Large Language Models (LLMs) for knowledge querying and analysis often encounter challenges in maintaining an LLM fine-tuned on targeted, up-to-date information that keeps answers relevant and grounded. Retrieval Augmented Generation (RAG) has quickly become a feasible solution for organizations looking to overcome the challenges of maintaining proprietary models and to help reduce LLM hallucinations in their query responses. However, RAG comes with its own issues regarding scaling data pipelines across tiered-access and disparate data sources. In many scenarios, it is necessary to query beyond a single data silo to provide richer and more relevant context for an LLM. Analyzing data sources within and across organizational trust boundaries is often limited by complex data-sharing policies that prohibit centralized data storage, therefore, inhibit the fast and effective setup and scaling of RAG solutions. In this paper, we introduce Confidential Computing (CC) techniques as a solution for secure Federated Retrieval Augmented Generation (FedRAG). Our proposed Confidential FedRAG system (C-FedRAG) enables secure connection and scaling of a RAG workflows across a decentralized network of data providers by ensuring context confidentiality. We also demonstrate how to implement a C-FedRAG system using the NVIDIA FLARE SDK and assess its performance using the MedRAG toolkit and MIRAGE benchmarking dataset.},

note = {arXiv:2412.13163 [cs]},

keywords = {and Cluster Computing, Computer Science - Distributed, Computer Science - Information Retrieval, Parallel},

pubstate = {published},

tppubtype = {misc}

}

@misc{roemmele_test-taking_2024-1,

title = {From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items},

author = {Melissa Roemmele and Andrew S. Gordon},

url = {https://arxiv.org/abs/2410.14897},

doi = {10.48550/ARXIV.2410.14897},

year  = {2024},

date = {2024-10-01},

urldate = {2024-12-05},

publisher = {arXiv},

abstract = {LLMs can now perform a variety of complex writing tasks. They also excel in answering questions pertaining to natural language inference and commonsense reasoning. Composing these questions is itself a skilled writing task, so in this paper we consider LLMs as authors of commonsense assessment items. We prompt LLMs to generate items in the style of a prominent benchmark for commonsense reasoning, the Choice of Plausible Alternatives (COPA). We examine the outcome according to analyses facilitated by the LLMs and human annotation. We find that LLMs that succeed in answering the original COPA benchmark are also more successful in authoring their own items.},

note = {Version Number: 1},

keywords = {DTIC, Learning Sciences},

pubstate = {published},

tppubtype = {misc}

}

@misc{lin_estuary_2024,

title = {Estuary: A Framework For Building Multimodal Low-Latency Real-Time Socially Interactive Agents},

author = {Spencer Lin and Basem Rizk and Miru Jun and Andy Artze and Caitlin Sullivan and Sharon Mozgai and Scott Fisher},

url = {http://arxiv.org/abs/2410.20116},

doi = {10.1145/3652988.3696198},

year  = {2024},

date = {2024-10-01},

urldate = {2024-12-06},

abstract = {The rise in capability and ubiquity of generative artificial intelligence (AI) technologies has enabled its application to the field of Socially Interactive Agents (SIAs). Despite rising interest in modern AI-powered components used for real-time SIA research, substantial friction remains due to the absence of a standardized and universal SIA framework. To target this absence, we developed Estuary: a multimodal (text, audio, and soon video) framework which facilitates the development of low-latency, real-time SIAs. Estuary seeks to reduce repeat work between studies and to provide a flexible platform that can be run entirely off-cloud to maximize configurability, controllability, reproducibility of studies, and speed of agent response times. We are able to do this by constructing a robust multimodal framework which incorporates current and future components seamlessly into a modular and interoperable architecture.},

note = {arXiv:2410.20116 [cs]},

keywords = {Virtual Agents},

pubstate = {published},

tppubtype = {misc}

}

@misc{chen_geometry-aware_2024,

title = {Geometry-aware Feature Matching for Large-Scale Structure from Motion},

author = {Gonglin Chen and Jinsen Wu and Haiwei Chen and Wenbin Teng and Zhiyuan Gao and Andrew Feng and Rongjun Qin and Yajie Zhao},

url = {https://arxiv.org/abs/2409.02310},

doi = {10.48550/ARXIV.2409.02310},

year  = {2024},

date = {2024-09-01},

urldate = {2025-01-16},

publisher = {arXiv},

abstract = {Establishing consistent and dense correspondences across multiple images is crucial for Structure from Motion (SfM) systems. Significant view changes, such as air-to-ground with very sparse view overlap, pose an even greater challenge to the correspondence solvers. We present a novel optimization-based approach that significantly enhances existing feature matching methods by introducing geometry cues in addition to color cues. This helps fill gaps when there is less overlap in large-scale scenarios. Our method formulates geometric verification as an optimization problem, guiding feature matching within detector-free methods and using sparse correspondences from detector-based methods as anchor points. By enforcing geometric constraints via the Sampson Distance, our approach ensures that the denser correspondences from detector-free methods are geometrically consistent and more accurate. This hybrid strategy significantly improves correspondence density and accuracy, mitigates multi-view inconsistencies, and leads to notable advancements in camera pose accuracy and point cloud density. It outperforms state-of-the-art feature matching methods on benchmark datasets and enables feature matching in challenging extreme large-scale settings.},

note = {Version Number: 3},

keywords = {DTIC},

pubstate = {published},

tppubtype = {misc}

}

@misc{gao_skyeyes_2024,

title = {Skyeyes: Ground Roaming using Aerial View Images},

author = {Zhiyuan Gao and Wenbin Teng and Gonglin Chen and Jinsen Wu and Ningli Xu and Rongjun Qin and Andrew Feng and Yajie Zhao},

url = {https://arxiv.org/abs/2409.16685},

doi = {10.48550/ARXIV.2409.16685},

year  = {2024},

date = {2024-09-01},

urldate = {2025-01-16},

publisher = {arXiv},

abstract = {Integrating aerial imagery-based scene generation into applications like autonomous driving and gaming enhances realism in 3D environments, but challenges remain in creating detailed content for occluded areas and ensuring real-time, consistent rendering. In this paper, we introduce Skyeyes, a novel framework that can generate photorealistic sequences of ground view images using only aerial view inputs, thereby creating a ground roaming experience. More specifically, we combine a 3D representation with a view consistent generation model, which ensures coherence between generated images. This method allows for the creation of geometrically consistent ground view images, even with large view gaps. The images maintain improved spatial-temporal coherence and realism, enhancing scene comprehension and visualization from aerial perspectives. To the best of our knowledge, there are no publicly available datasets that contain pairwise geo-aligned aerial and ground view imagery. Therefore, we build a large, synthetic, and geo-aligned dataset using Unreal Engine. Both qualitative and quantitative analyses on this synthetic dataset display superior results compared to other leading synthesis approaches. See the project page for more results: https://chaoren2357.github.io/website-skyeyes/.},

note = {Version Number: 1},

keywords = {DTIC},

pubstate = {published},

tppubtype = {misc}

}

@misc{liu_alignbench_2024,

title = {AlignBench: Benchmarking Chinese Alignment of Large Language Models},

author = {Xiao Liu and Xuanyu Lei and Shengyuan Wang and Yue Huang and Zhuoer Feng and Bosi Wen and Jiale Cheng and Pei Ke and Yifan Xu and Weng Lam Tam and Xiaohan Zhang and Lichao Sun and Xiaotao Gu and Hongning Wang and Jing Zhang and Minlie Huang and Yuxiao Dong and Jie Tang},

url = {http://arxiv.org/abs/2311.18743},

doi = {10.48550/arXiv.2311.18743},

year  = {2024},

date = {2024-08-01},

urldate = {2025-01-16},

publisher = {arXiv},

abstract = {Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants. However, the effective evaluation of alignment for emerging Chinese LLMs is still largely unexplored. To fill in this gap, we introduce AlignBench, a comprehensive multi-dimensional benchmark for evaluating LLMs' alignment in Chinese. We design a human-in-the-loop data curation pipeline, containing eight main categories, 683 real-scenario rooted queries and corresponding human verified references. To ensure the correctness of references, each knowledge-intensive query is accompanied with evidences collected from reliable web sources (including URLs and quotations) by our annotators. For automatic evaluation, our benchmark employs a rule-calibrated multi-dimensional LLM-as-Judgetextasciitildetextbackslashcitezheng2023judging approach with Chain-of-Thought to generate explanations and final ratings, ensuring high reliability and interpretability. All evaluation code, data, and LLM generations are available at textbackslashurlhttps://github.com/THUDM/AlignBench. Since its release, AlignBench has been adopted by top (Chinese) LLMs for evaluating their alignment capabilities in Chinese, including ChatGLM, Qwen, DeepSeek, Yi, Baichuan, and Abab.},

note = {arXiv:2311.18743 [cs]},

keywords = {Machine Learning},

pubstate = {published},

tppubtype = {misc}

}

@misc{han_knowledge-based_2024,

title = {Knowledge-based Emotion Recognition using Large Language Models},

author = {Bin Han and Cleo Yau and Su Lei and Jonathan Gratch},

url = {http://arxiv.org/abs/2408.04123},

year  = {2024},

date = {2024-08-01},

urldate = {2024-08-15},

publisher = {arXiv},

abstract = {Emotion recognition in social situations is a complex task that requires integrating information from both facial expressions and the situational context. While traditional approaches to automatic emotion recognition have focused on decontextualized signals, recent research emphasizes the importance of context in shaping emotion perceptions. This paper contributes to the emerging field of context-based emotion recognition by leveraging psychological theories of human emotion perception to inform the design of automated methods. We propose an approach that combines emotion recognition methods with Bayesian Cue Integration (BCI) to integrate emotion inferences from decontextualized facial expressions and contextual knowledge inferred via Large-language Models. We test this approach in the context of interpreting facial expressions during a social task, the prisoner's dilemma. Our results provide clear support for BCI across a range of automatic emotion recognition methods. The best automated method achieved results comparable to human observers, suggesting the potential for this approach to advance the field of affective computing.},

note = {arXiv:2408.04123 [cs]},

keywords = {DTIC, Emotions},

pubstate = {published},

tppubtype = {misc}

}

@misc{tak_gpt-4_2024,

title = {GPT-4 Emulates Average-Human Emotional Cognition from a Third-Person Perspective},

author = {Ala N. Tak and Jonathan Gratch},

url = {http://arxiv.org/abs/2408.13718},

year  = {2024},

date = {2024-08-01},

urldate = {2024-09-17},

publisher = {arXiv},

abstract = {This paper extends recent investigations on the emotional reasoning abilities of Large Language Models (LLMs). Current research on LLMs has not directly evaluated the distinction between how LLMs predict the self-attribution of emotions and the perception of others' emotions. We first look at carefully crafted emotion-evoking stimuli, originally designed to find patterns of brain neural activity representing fine-grained inferred emotional attributions of others. We show that GPT-4 is especially accurate in reasoning about such stimuli. This suggests LLMs agree with humans' attributions of others' emotions in stereotypical scenarios remarkably more than self-attributions of emotions in idiosyncratic situations. To further explore this, our second study utilizes a dataset containing annotations from both the author and a third-person perspective. We find that GPT-4's interpretations align more closely with human judgments about the emotions of others than with self-assessments. Notably, conventional computational models of emotion primarily rely on self-reported ground truth as the gold standard. However, an average observer's standpoint, which LLMs appear to have adopted, might be more relevant for many downstream applications, at least in the absence of individual information and adequate safety considerations.},

note = {arXiv:2408.13718 [cs]},

keywords = {DTIC, Emotions},

pubstate = {published},

tppubtype = {misc}

}