Papers
Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning
Zinan Tang, Xin Gao, Qizhi Pei et al.
Why and How LLMs Benefit from Knowledge Introspection in Commonsense Reasoning
Chengfeng Zhao, Shizhu He, Shanshan Jiang et al.
DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction
Yiqi Li, Yusheng Liao, Zhe Chen et al.
Realistic Training Data Generation and Rule Enhanced Decoding in LLM for NameGuess
Yikuan Xia, Jiazun Chen, Sujian Li et al.
SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
Yicheng Ji, Jun Zhang, Heming Xia et al.
From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora
Yingli Shen, Wen Lai, Shuo Wang et al.
Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment
Wenrui Cai, Chengyu Wang, Junbing Yan et al.
Probabilistic Soundness Guarantees in LLM Reasoning Chains
Weiqiu You, Anton Xue, Shreya Havaldar et al.
An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint
Yi Sun, Han Wang, Jiaqiang Li et al.
Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching
Songze Li, Zhiqiang Liu, Zhengke Gui et al.
Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making
Yuanjun Feng, Vivek Choudhary, Yash Raj Shrestha
Structuring Radiology Reports: Challenging LLMs with Lightweight Models
Johannes Moll, Louisa Fay, Asfandyar Azhar et al.
PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks
Yunuo Liu, Dawei Zhu, Zena Al-Khalili et al.
Can LLMs Explain Themselves Counterfactually?
Zahra Dehghanighobadi, Asja Fischer, Muhammad Bilal Zafar
Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment
Hao Li, Lijun Li, Zhenghao Lu et al.
A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages
Tatiana Anikina, Jan Cegin, Jakub Simko et al.
A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality
Hanbo Huang, Yihan Li, Bowen Jiang et al.
A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation
Yan Li, Tianyi Zhang, Zechuan Li et al.
IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages
Muhammad Falensi Azmi, Muhammad Dehan Al Kautsar, Alfan Farizki Wicaksono et al.
Steering LLM Reasoning Through Bias-Only Adaptation
Viacheslav Sinii, Alexey Gorbatovski, Artem Cherepanov et al.
FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs’ Responsiveness to Human Feedback
Youquan Li, Miao Zheng, Fan Yang et al.
LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding
Yuxuan Hu, Jihao Liu, Ke Wang et al.
Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs
Dawid Jan Kopiczko, Tijmen Blankevoort, Yuki M Asano
Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey
Mehrab Tanjim, Yeonjun In, Xiang Chen et al.
Enhancing LLM Text Detection with Retrieved Contexts and Logits Distribution Consistency
Zhaoheng Huang, Yutao Zhu, Ji-Rong Wen et al.