Search research

Topics & fields

Scaling Laws471 papers Scaling Laws142 papers Neural Scaling Laws233 papers Large-Scale Image Generation131 papers Test-Time Scaling96 papers Large-Scale Video Generation Models69 papers Large-Scale Benchmark64 papers Large-Scale Recommendation Systems62 papers Temporal Scales25 papers Organizational Scale23 papers Rate Scaling23 papers Efficient Scaling22 papers

13,441–13,470 of 13,535

Papers

Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction
Date pendingRyo Kamoi, Ameya Godbole, Binglin Zhou +5User Simulation
CLIP-RD: Relational Distillation for Efficient CLIP Knowledge Distillation
Date pendingJeannie Chung, Hanna Jang, Ingyeong Yang +2Modality Gap
FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving
Date pendingQingxiu Liu, Yongchao He, Runhan Jiang +4Mixture-Of-Expert Inference Mixture-of-Experts Models
Exploring Urban Land Use Patterns by Pattern Mining and Unsupervised Learning
Date pendingZdena Dobesova, Tai Dinh, Pavel NovakUrban Environments Data Mining
Reconstruction of a 3D wireframe from a single line drawing via generative depth estimation
Date pendingElton Cao, Hod LipsonDepth Estimation Sketches
SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics
Date pendingHaolong Hu, Hanyu Li, Tiancheng He +6Mllm-Based Feedback Learning
ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning
Date pendingXianming Li, Zongxi Li, Tsz-fung Andrew Lee +3Parameter-Efficient Fine-Tuning
Uni-HOI:A Unified framework for Learning the Joint distribution of Text and Human-Object Interaction
Date pendingMengfei Zhang, Jinlu Zhang, Zhigang TuArticulated Objects Unified Multimodal Models
Timing is Everything: Temporal Scaffolding of Semantic Surprise in Humor
Date pendingYuxi Ma, Yongqian Peng, Junchen Lyu +2Humor Surprisal
Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
Date pendingPhilip Jordan, Maryam KamgarpourNash Equilibrium Partially Observable Markov Decision Process
DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized Momentum
Date pendingJihwan Kim, Chenglin FanDifferential Privacy Muon Optimizer
Text-to-SPARQL Generation with Reinforcement Learning: A GRPO-based Approach on DBLP
Date pendingJann Pfeifer, Debayan Banerjee, Ricardo UsbeckSparql Knowledge Graphs
Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning
Date pendingAnthony GX-Chen, Ankit Anand, Gheorghe Comanici +7Deep Reinforcement Learning
ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces
Date pendingJinu Lee, Shivam Agarwal, Amruta Parulekar +3Reasoning Traces Large Language Model Reasoning
Some hypotheses on how chatbots work in problem-solution-driven conversations: Large Language Models as confirmation of the Innovation Illusion
Date pendingS. F. M. van Vlijmen, H. D. Lethe jrChatbots Metaphors
A Lightweight Multi-Agent Framework for Automated Concrete Barrier Design
Date pendingWanting Wang, Xiye Ma, Yuyang He +1Modular Agentic Framework Computer-Aided Design
State-specific respiratory signatures for affective and stress recognition: Interpretable respiratory markers, autocorrelation lags, and compact CNN models
Date pendingAndrei Velichko, Mehmet Tahir HuyutRespiratory Sound Classification Trier Social Stress Test
DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning
Date pendingBingchen Huang, Yifu Chen, Zhiling Wang +1Domain Incremental Learning Self-Supervised Vision Transformers
Diffusion learning reveals viable parameter manifolds and compensation geometry in biological dynamical systems
Date pendingRuilin Zhang, Louis Tao, Zhuo-Cheng XiaoQualitative Dynamics Discrete Diffusion Model
ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions
Date pendingThomas Thebaud, Junhyeok Lee, Laureano Moro-Velazquez +2Zero-Shot Text-To-Speech Speaker Attributes
EVIS: Real-Time Event Camera Simulation with Multimodal Supervision in NVIDIA Isaac Sim
Date pendingLinli Shi, Ruijun Zhang, Ziyun WangNvidia Isaac Sim Ego-Motion
Learning Traversability for Long Horizon Off-Road Navigation
Date pendingKasi Viswanath, Jason M. Gregory, Shaunak Kolhe +1Traversability Autonomous Navigation
HeteroPROMPT: A Real-time and Privacy-Preserving Heterogeneous Collaborative Perception Framework
Date pendingArmin Maleki, Hayder RadhaCollaborative Perception Fusion
SeDeM: Selective Decompression of Hidden-State Memories for Long-Context Question Answering
Date pendingMaryam Haghifam, Jason Cong, Yizhou SunEfficient Long-Context Inference Context Length
SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models
Date pendingXingyan Li, Jordan A. Caraballo-Vega, Jie Gong +2Geospatial Foundation Models Cross-Sensor Generalization
Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Construction
Date pendingYi LiuConstraint-Aware Synthesis Construction
Self-Evolving Embodied Agents via Skill-Harness Evolution
Date pendingPeidong Wang, Zhiming Ma, Ying Chang +7Self-Evolving Agents Embodied Agents
Measuring Browser Webcam Gaze Honestly: A Capture-Clock Methodology and Open Reference Implementation
Date pendingChi-Sheng Chen, Gabriel A. BratGaze Low-Latency Systems
StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs
Date pendingJoya Chen, Zeyun Zhong, Mike Zheng ShouLarge Vision Language Models Video Question Answering
Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models
Date pendingVarvara Arzt, Allan Hanbury, Terra BlevinsEnglish Unified Transformer

Date pending · cs.CLJ/K move · Enter open · S save

Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction

Ryo Kamoi, Ameya Godbole, Binglin Zhou, Xiaoxin Lu+4

Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. This paper reconsiders the evaluation of simulated conversations by explicitly recognizing that human conversations inherently involve inconsistent and uncollaborative behaviors, such as misunderstandings and interruptions. Since these behaviors contribute to the complexity of human social interaction, we argue that LLM-simulated conversations should reproduce them at frequencies comparable to those observed in human conversations. To support a detailed and interpretable evaluation of these behaviors, we introduce CoCoEval, a framework consisting of an evaluation scheme based on turn-level detection of 10 types of inconsistent and uncollaborative behaviors and a benchmark for simulating conversations in professional scenarios involving collaboration and conflict. Using CoCoEval, we compare human conversations with those simulated by GPT-4.1, GPT-5.1, and Claude Opus 4. The results show that (1) LLM-simulated conversations exhibit far fewer inconsistent and uncollaborative behaviors than human conversations under vanilla prompting, and (2) prompt engineering and supervised fine-tuning do not provide reliable control over these behaviors, often leading to the overproduction of specific behaviors. CoCoEval identifies gaps between human and LLM-simulated conversations that are not captured by conventional evaluation based on conversation-level Likert scales, raising concerns about the use of LLMs as proxies for human social interaction.

User Simulation

Open paper Ask about it PDF