7 papers
Learned Reporting Preferences in RLVR Can Conflict with the Current Request
Yupeng Chang, Wenxuan Zhang, Yuan Wu
Reinforcement learning with verifiable rewards (RLVR) has become a prominent approach for improving language-model performance on reasoning tasks using automatically checked answer…
From Checkpoint Variation to Selection Gains in Supervised Fine-Tuning
Yupeng Chang, Wenxuan Zhang, Yuan Wu
Checkpoint selection is a routine decision in supervised fine-tuning (SFT): training produces multiple checkpoints, but only one is retained. Yet fixed-budget comparisons do not by…
GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models
Ryner Tan, Wenxuan Zhang
Large Audio-Language Models (LALMs) integrate audio perception and language understanding within a unified framework, enabling a wide range of real-world applications. Despite rece…
Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces
Chen He, Yuhao Wu, Lei Wang +2
Long chain-of-thought (CoT) traces are widely used as supervision for reasoning-oriented LLM SFT, yet answer-correct traces can still lead to markedly different fine-tuning outcome…
dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models
Wenxuan Zhang, Lemeng Wu, Changsheng Zhao +11
Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation, which in turn presents new challenges for aligning them with human preferences. In this wo…
Logic-Oriented Retriever Enhancement via Contrastive Learning
Wenxuan Zhang, Yuan-Hao Jiang, Changyong Qi +2
Large language models (LLMs) struggle in knowledge-intensive tasks, as retrievers often overfit to surface similarity and fail on queries involving complex logical relations. The c…
FreeChunker: A Cross-Granularity Chunking Framework
Wenxuan Zhang, Yuan-Hao Jiang, Yang Cao +1
Chunking strategies significantly impact the effectiveness of Retrieval-Augmented Generation (RAG) systems. Existing methods operate within fixed-granularity paradigms that rely on…