8 papers
Verifier-Induced Support Reshaping in On-Policy Optimization
Shaohang Wei, Zikun Su, Feifan Song +4
We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objectives too rare to sa…
Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction
Guangyue Peng, Wei Li, Wen Luo +1
Grammatical Error Correction (GEC) involves detecting and correcting the wrong usage of grammar. While large language models (LLMs) with in-context learning (ICL) capabilities have…
Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
Wen Luo, Guangyue Peng, Liang Wang +7
Large Reasoning Models achieve strong performance on complex tasks but remain prone to hallucinations, particularly in long-form generation where errors compound across reasoning s…
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
Wen Luo, Guangyue Peng, Wei Li +8
Despite their impressive capabilities, large language models (LLMs) frequently generate hallucinations. Previous work shows that their internal states encode rich signals of truthf…
FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation
Wei Li, Xin Zhang, Zhongxin Guo +6
Implementing new features in repository-level codebases is a crucial application of code generation models. However, current benchmarks lack a dedicated evaluation framework for th…
Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation
Wen Luo, Feifan Song, Wei Li +3
Large Language Models (LLMs) are increasingly required to generate text that is both factually accurate and diverse across various open-ended applications. However, current stochas…