10 papers
Strong yet Controllable LLM Abstention without Learning to Abstain
Junwei Zhang, Yifei Wang, Wanli Yang +6
Large language models (LLMs) can reduce hallucination by abstaining from questions they would likely get wrong. Abstention can be implemented outside the model (selective answering…
Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence
Xinyu Liu, Kechen Jiao, Chunyang Xiao +10
On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learn…
LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
Yuchun Fan, Bei Li, Peiguang Li +9
Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts.…
MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
Junhao Ruan, Abudukeyumu Abudula, Bei Li +8
Accurate evaluation of conversational retrieval is pivotal for advancing Retrieval-Augmented Generation (RAG) systems. However, existing conversational retrieval benchmarks suffer…
Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization
Yang Bai, Kaiyuan Liu, Ziyuan Zhuang +5
Complex reinforcement learning environments frequently employ multi-task and mixed-reward formulations. In these settings, heterogeneous reward distributions and correlated reward…
Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders
Shunchang Liu, Xin Chen, Belen Martin Urcelay +1
Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit preference instability, producing contr…
SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control
Jingyan Zhang, Han Liang, Ruichi Zhang +6
Controlling physics-based humanoids from natural-language instructions is a critical step toward general-purpose embodied agents. However, existing methods remain constrained by a…
BaseCal: Unsupervised Confidence Calibration via Base Model Signals
Hexiang Tan, Wanli Yang, Junwei Zhang +7
Reliable confidence is essential for trusting the outputs of LLMs, yet widely deployed post-trained LLMs (PoLLMs) typically compromise this trust with severe overconfidence. In con…
OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation
Han Li, Xinyu Peng, Yaoming Wang +7
We introduce OneCAT, a unified multimodal model that seamlessly integrates understanding, generation, and editing within a novel, pure decoder-only transformer architecture. Our fr…
Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs
Hexiang Tan, Fei Sun, Sha Liu +8
As large language models (LLMs) often generate plausible but incorrect content, error detection has become increasingly critical to ensure truthfulness. However, existing detection…