Papers
Linear Steerability in Language Models: When It Emerges and How It Evolves
Jianshu She, Xinyue Li, Eric P. Xing et al.
Semantic-Aware Action Space Compression via LLM-DRL Synergy for Efficient Task-oriented Dialogue Policy Exploration
Yangyang Zhao, Ben Niu, Yuxuan Tan et al.
Layer Duplication in LLMs
Neo Eyal, Nachum Dershowitz, Kfir Bar
Hierarchical Reward Modeling for Fault Localization in Large Code Repositories
Jiwei Zhang, Jianxun Lian, Haiming Qin et al.
ThinkQE: Query Expansion via an Evolving Thinking Process
Yibin Lei, Tao Shen, Andrew Yates
Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modeling
Florian Eichin, Carolin M. Schuster, Georg Groh et al.
Can Role Vectors Affect LLM Behaviour?
Daniele Potertì, Andrea Seveso, Fabio Mercorio
Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models
Runsong Zhao, Xin Liu, Xinyu Liu et al.
ET-MIER: Entity Type-guided Key Mention Identification and Evidence Retrieval for Document-level Relation Extraction
Xin Li, Huangming Xu, Fu Zhang et al.
Beneath the Facade: Probing Safety Vulnerabilities in LLMs via Auto-Generated Jailbreak Prompts
Heehyeon Kim, Kyeongryul Lee, Joyce Jiyoung Whang
Sparsifying Mamba
An Wang, Ruobing Xie, Shuaipeng Li et al.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Hongfei Xia, Hongru Wang, Zeming Liu et al.
Distributed LLM Serving on Consumer-Grade GPUs by Reconciling Computation and Communication
Lewei Jin, Kui Zhang, Yongqi Chen et al.
Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction
Yuanbo Xie, Yingjie Zhang, Tianyun Liu et al.
Analyzing Gambling Addictions: A Spanish Corpus for Understanding Pathological Behavior
Manuel Couto, Marcos Fernández-Pichel, Mario Ezra Aragon et al.
Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd
Yejin Son, Saejin Kim, Dongjun Min et al.
MAFMO: Multi-modal Adaptive Fusion with Meta-template Optimization for Vision-Language Models
Mingrui Xie, Lulu Xu, Junliang Du
Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution
Zuzanna Dubanowska, Maciej Żelaszczyk, Michał Brzozowski et al.
Beyond Binary Preferences: Semi-Online Label-Free GRACE-KTO with Group-Wise Adaptive Calibration for High-Quality Long-Text Generation
Jingyang Deng, Ran Chen, Jo-Ku Cheng et al.
A Benchmark for Hindi Verb-Argument Structure Alternations
Kanishka Jain, Ashwini Vaidya
Understanding and Improving Information Preservation in Prompt Compression for LLMs
Weronika Łajewska, Momchil Hardalov, Laura Aina et al.
Transfer-Aware Data Selection for Domain Adaptation in Text Retrieval
Linzhu Yu, Huan Li, Ke Chen et al.
Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches
Israel Abebe Azime, Deborah D. Kanubala, Tejumade Afonja et al.
LLMs Reproduce Stereotypes of Sexual and Gender Minorities
Ruby Ostrow, Adam Lopez