Papers
Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
Nikita Afonin, Nikita Andriianov, Vahagn Hovhannisyan et al.
Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses
Chongyuan Dai, Yaling Shen, Zihan Gao et al.
When Background Matters: Breaking Medical Vision Language Models by Transferable Attack
Akash Ghosh, Subhadip Baidya, Sriparna Saha et al.
Theory-optimal Quantization Based on Flatness
Xiusheng Huang, Zhe Li, Xuanwu Yin et al.
Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models
Yongjiang Liu, Haoxi Li, Xiaosong Ma et al.
TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice
Gang Hu, Yating Chen, Haiyan Ding et al.
Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models
Eric Hanchen Jiang, Levina Li, Frank Wan et al.
UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages
Pranjal A Chitale, Varun Gumma, Sanchit Ahuja et al.
AlignCultura: Towards Culturally Aligned Large Language Models?
Gautam Siddharth Kashyap, Mark Dras, Usman Naseem
Cross-Examination Framework: A Task-Agnostic Diagnostic for Information Fidelity in Text-to-Text Generation
Tathagata Raha, Clement Christophe, Nada Saadi et al.
Refining and Reusing Annotation Guidelines for LLM Annotation
Kon Woo Kim, Jin-Dong Kim, Akiko Aizawa
Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy
Eric Hanchen Jiang, Weixuan Ou, Run Liu et al.
AdaDPI: Document-level Translation Adaptive Agent via Dynamic Parametric Internalization
Hong Ren, Liting Deng, Shaolin Zhu et al.
FairQE: Multi-Agent Framework for Mitigating Gender Bias in Translation Quality Estimation
Jinhee Jang, Juhwan Choi, Dongjin Lee et al.
Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives
Changgeon Ko, Jisu Shin, Hoyun Song et al.
StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
Kaiyi Zhang, Ang Lv, Jinpeng Li et al.
Revealing Procedural Reasoning Structures in Chain-of-Thought Training via Span-Level Gradient Organization
Jia Liu, Jiaxin Luo, Weiwen Xu et al.
Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation
Jiawei Zhou, Chi Zhang, Xiang Feng et al.
CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
Zhenpeng Su, Leiyu Pan, Minxuan Lv et al.
Can Compact Language Models Search Like Agents? Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities
Rikuto Kotoge, Mai Nishimura, Jiaxin Ma
Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards
Tianhao Niu, Ziyu Han, Qiguang Chen et al.
MARD: Module-Aware Reasoning Distillation for Language Models with Adaptive Supervision
Wenqi Yang, Jianjun Li, Zhibo Zhang et al.
Zero-Shot Detection of LLM-Generated Text using Temperature Sensitivity
Shixuan Ma, Jiahao Li, Zhendong Mao et al.
Execution as Verification: Fine-Grained Self-Correcting Reasoning for Complex KBQA
Minghan Zhang, Zhen Yang, Haodong Zou et al.
River-LLM: Large Language Model Seamless Exit Based on KV Share
Yingtao Shen, An Zou