7 papers
Do LLMs Signal When They're Right? Evidence from Neuron Agreement
Kang Chen, Yaoning Wang, Kai Xiong +4
Large language models (LLMs) commonly boost reasoning via sample-evaluate-ensemble decoders, achieving label free gains without ground truth. However, prevailing strategies score c…
Expressive Value Learning for Scalable Offline Reinforcement Learning
Nicolas Espinosa-Dice, Kiante Brantley, Wen Sun
Reinforcement learning (RL) is a powerful paradigm for learning to make sequences of decisions. However, RL has yet to be fully leveraged in robotics, principally due to its lack o…
Prompt Curriculum Learning for Efficient LLM Post-Training
Zhaolin Gao, Joongwon Kim, Wen Sun +4
We introduce Prompt Curriculum Learning (PCL), a lightweight reinforcement learning (RL) algorithm that selects intermediate-difficulty prompts using a learned value model to post-…
SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models
Peng Ding, Wen Sun, Dailin Li +4
Large Language Models (LLMs) excel at various natural language processing tasks but remain vulnerable to jailbreaking attacks that induce harmful content generation. In this paper,…
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Tencent Hunyuan Team, Ao Liu, Botong Zhou +248
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mam…
Efficient Imitation under Misspecification
Nicolas Espinosa-Dice, Sanjiban Choudhury, Wen Sun +1
We consider the problem of imitation learning under misspecification: settings where the learner is fundamentally unable to replicate expert behavior everywhere. This is often true…