Papers
Dissecting Persona-Driven Reasoning in Language Models via Activation Patching
Ansh Poonia, Maeghal Jain
KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing
Mengqi Zhang, Bowen Fang, Qiang Liu et al.
Investigating Multi-layer Representations for Dense Passage Retrieval
Zhongbin Xie, Thomas Lukasiewicz
Leveraging Unpaired Feedback for Long-Term LLM-based Recommendation Tuning
Jizhi Zhang, Chongming Gao, Wentao Shi et al.
StructuThink: Reasoning with Task Transition Knowledge for Autonomous LLM-Based Agents
Haiyu Zhao, Zhenyu Guo, Chunhong Zhang et al.
Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees
Ahmed Heakl, Sarim Hashmi, Chaimaa Abi et al.
Improving Preference Alignment of LLM with Inference-Free Self-Refinement
Fukun Ma, Kaibin Tian, Jieting Xue et al.
AgentDrug: Utilizing Large Language Models in an Agentic Workflow for Zero-Shot Molecular Optimization
Le Huy Khiem, Ting Hua, Nitesh V Chawla
A Similarity Measure for Comparing Conversational Dynamics
Sang Min Jung, Kaixiang Zhang, Cristian Danescu-Niculescu-Mizil
SpecCoT: Accelerating Chain-of-Thought Reasoning through Speculative Exploration
Junhan Shi, Yijia Zhu, Zhenning Shi et al.
Insights into using temporal coordinated behaviour to explore connections between social media posts and influence
Elisa Sartori, Serena Tardelli, Maurizio Tesconi et al.
Exploring Context Strategies in LLMs for Discourse-Aware Machine Translation
Ritvik Choudhary, Rem Hida, Masaki Hamada et al.
Nexus: Adaptive Upcycling to Efficiently Pretrain Mixture of Experts
Nikolas Gritsch, Qizhen Zhang, Acyr Locatelli et al.
Think Right, Not More: Test-Time Scaling for Numerical Claim Verification
Primakov Chungkham, Venktesh V, Vinay Setty et al.
Under the Shadow of Babel: How Language Shapes Reasoning in LLMs
Chenxi Wang, Yixuan Zhang, Lang Gao et al.
ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects
Jipeng Zhang, Haolin Yang, Kehao Miao et al.
TIU-Bench: A Benchmark for Evaluating Large Multimodal Models on Text-rich Image Understanding
Kun Zhang, Liqiang Niu, Zhen Cao et al.
Estimating Machine Translation Difficulty
Lorenzo Proietti, Stefano Perrella, Vilém Zouhar et al.
From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformation
Zhihao Zhang, Yiran Zhang, Xiyue Zhou et al.
SciCompanion: Graph-Grounded Reasoning for Structured Evaluation of Scientific Arguments
Joshua Alan Flashner, Adithya Kulkarni, Dawei Zhou
Evaluating Compound AI Systems through Behaviors, Not Benchmarks
Pranav Bhagat, K N Ajay Shastry, Pranoy Panda et al.
Facilitating Cross-lingual Transfer of Empathy through Language-independent Latent Diffusion: A Case Study in Chinese
Junlin Li, Peng Bo, Yu-Yin Hsu
DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction
Jian Chen, Zhenyan Chen, Xuming Hu et al.
BannerBench: Benchmarking Vision Language Models for Multi-Ad Selection with Human Preferences
Hiroto Otake, Peinan Zhang, Yusuke Sakai et al.