most citedProbability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs

Haoming Meng, Kexin Huang, Shaohang Wei +6

Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvem…

cs.CL2025

Mitigating Overthinking through Reasoning Shaping

Feifan Song, Shaohang Wei, Bofei Gao +8

Large reasoning models (LRMs) boosted by Reinforcement Learning from Verifier Reward (RLVR) have shown great power in problem solving, yet they often cause overthinking: excessive,…

cs.CL2025

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding

Feifan Song, Shaohang Wei, Wen Luo +4

Large Language Models (LLMs) require alignment with human preferences to avoid generating offensive, false, or meaningless content. Recently, low-resource methods for LLM alignment…

cs.CL2025

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…