Papers
Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs
Yiheng Yang, Yujie Wang, Chi Ma et al.
FLUKE: A Linguistically-Driven and Task-Agnostic Framework for Robustness Evaluation
Yulia Otmakhova, Thinh Hung Truong, Rahmad Mahendra et al.
Stay Focused: Problem Drift in Multi-Agent Debate
Jonas Becker, Lars Benedikt Kaesberg, Andreas Stephan et al.
Benchmarking Direct Preference Optimization for Medical Large Vision–Language Models
Dain Kim, Jiwoo Lee, Jaehoon Yun et al.
Multilingual Self-Taught Faithfulness Evaluators
Carlo Alfano, Aymen Al Marjani, Zeno Jonke et al.
Show or Tell? Modeling the evolution of request-making in Human-LLM conversations
Shengqi Zhu, Jeffrey Rzeszotarski, David Mimno
CLICKER: Cross-Lingual Knowledge Editing via In-Context Learning with Adaptive Stepwise Reasoning
Zehui Jiang, Xin Zhao, Yuta Kumadaki et al.
Think Just Enough: Leveraging Self-Assessed Confidence for Adaptive Reasoning in Language Models
Junyeob Kim, Sang-goo Lee, Taeuk Kim
Open-Domain Safety Policy Construction
Di Wu, Siyue Liu, Zixiang Ji et al.
Position Encoding with Random Float Sampling Enhances Length Generalization of Transformers
Atsushi Shimizu, Shohei Taniguchi, Yutaka Matsuo
Enabling Autoregressive Models to Fill In Masked Tokens
Daniel Mingyi Israel, Aditya Grover, Guy Van den Broeck
R-GDA: Reflective Guidance Data Augmentation with Multi-Agent Feedback for Domain-Specific Named Entity Recognition
Hyeonseok Kang, Hyuk Namgoong, Goun Pyeon et al.
From Numbers to Narratives: Efficient Language Model-Based Detection for Safety-Critical Minority Classes
Ahatsham Hayat, Hunter Tridle, Mohammad Rashedul Hasan
Program-of-Thought Reveals LLM Abstraction Ceilings
Mike Zhou, Fenil Bardoliya, Vivek Gupta et al.
Beyond Sampling: Self-Sorting for Long-Context Ranking
Juseon Do, Sungwoo Han, Jingun Kwon et al.
ConRAS: Contrastive In-context Learning Framework for Retrieval-Augmented Summarization
Juseon Do, Sungwoo Han, Jingun Kwon et al.
We Are What We Repeatedly Do: Improving Long Context Instruction Following
Preston K Robinette, Andrew Hard, Swaroop Ramaswamy et al.
A Multi-Task Learning Framework for Modeling Engagement and Topic-Sensitive Responses in Arabic Women’s Discourse
Mabrouka Bessghaier, Md. Rafiul Biswas, Shimaa Ibrahim et al.
Completely Modular Fine-tuning for Dynamic Language Adaptation
Zhe Cao, Yusuke Oda, Qianying Liu et al.
What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance
William Watson, Nicole Cho, Sumitra Ganesh et al.
Thunder-NUBench: A Benchmark for LLMs’ Sentence-Level Negation Understanding
Yeonkyoung So, Gyuseong Lee, Sungmok Jung et al.
Benchmarking the Energy Savings with Speculative Decoding Strategies
Rohit Dutta, Paramita Koley, Soham Poddar et al.
UniToolBench: A Benchmark for Tool-Augmented LLMs in Cross-Domain, Universal Task Automation
Xiaojie Guo, Yang Zhang, Bing Zhang et al.
SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph
Jiazheng Li, Yawei Wang, Qiaojing Yan et al.
Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization
Jiwei Guan, Haibo Jin, Haohan Wang