256 citations · 435 across the 38 of their papers we have counts for
38 papers
Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning
Zhiheng Xi, Jixuan Huang, Xin Guo +15
Training critiquing language models to assess and provide feedback on model outputs is a promising way to improve LLMs for complex reasoning tasks. However, existing approaches typ…
What Makes a Good Speech Tokenizer for LLM-Centric Speech Generation? A Systematic Study
Xiaoran Fan, Zhichao Sun, Yangfan Gao +19
Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal ali…
Better Process Supervision with Bi-directional Rewarding Signals
Wenxiang Chen, Wei He, Zhiheng Xi +9
Process supervision, i.e., evaluating each step, is critical for complex large language model (LLM) reasoning and test-time searching with increased inference compute. Existing app…
Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
Zhiheng Xi, Dingwen Yang, Jixuan Huang +21
Training large language models (LLMs) to spend more time thinking and reflection before responding is crucial for effectively solving complex reasoning tasks in fields such as scie…
Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Shuo Li, Tao Ji, Xiaoran Fan +10
In the study of LLMs, sycophancy represents a prevalent hallucination that poses significant challenges to these models. Specifically, LLMs often fail to adhere to original correct…
RMB: Comprehensively Benchmarking Reward Models in LLM Alignment
Enyu Zhou, Guodong Zheng, Binghai Wang +11
Reward models (RMs) guide the alignment of large language models (LLMs), steering them toward behaviors preferred by humans. Evaluating RMs is the key to better aligning LLMs. Howe…
What's Wrong with Your Code Generated by Large Language Models? An Extensive Study
Shihan Dou, Haoxiang Jia, Shenxi Wu +14
The increasing development of LLMs in code generation has drawn significant attention among researchers. To enhance LLM-based code generation ability, current efforts are predomina…
Aligning Large Language Models from Self-Reference AI Feedback with one General Principle
Rong Bao, Rui Zheng, Shihan Dou +6
In aligning large language models (LLMs), utilizing feedback from existing advanced AI rather than humans is an important method to scale supervisory signals. However, it is highly…
Uncertainty Aware Learning for Language Model Alignment
Yikun Wang, Rui Zheng, Liang Ding +3
As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges. Existing alignment strategies, which typically lever…
AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
Zhiheng Xi, Yiwen Ding, Wenxiang Chen +17
Building generalist agents that can handle diverse tasks and evolve themselves across different environments is a long-term goal in the AI community. Large language models (LLMs) a…
SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
Caishuang Huang, Wanxu Zhao, Rui Zheng +11
As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. How…
SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model
Yongting Zhang, Lu Chen, Guodong Zheng +10
The emergence of Vision Language Models (VLMs) has brought unprecedented advances in understanding multimodal information. The combination of textual and visual semantics in VLMs i…
MetaRM: Shifted Distributions Alignment via Meta-Learning
Shihan Dou, Yan Liu, Enyu Zhou +9
The success of Reinforcement Learning from Human Feedback (RLHF) in language model alignment is critically dependent on the capability of the reward model (RM). However, as the tra…
Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals
Rui Zheng, Yuhao Zhou, Zhiheng Xi +3
Deep neural networks (DNNs) are notoriously vulnerable to adversarial attacks that place carefully crafted perturbations on normal examples to fool DNNs. To better understand such…
EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
Weikang Zhou, Xiao Wang, Limao Xiong +18
Jailbreak attacks are crucial for identifying and mitigating the security vulnerabilities of Large Language Models (LLMs). They are designed to bypass safeguards and elicit prohibi…
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
Zhiheng Xi, Wenxiang Chen, Boyang Hong +18
In this paper, we propose R: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the bene…
StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
Shihan Dou, Yan Liu, Haoxiang Jia +14
The advancement of large language models (LLMs) has significantly propelled the field of code generation. Previous work integrated reinforcement learning (RL) with compiler feedbac…
MouSi: Poly-Visual-Expert Vision-Language Models
Xiaoran Fan, Tao Ji, Changhao Jiang +21
Current large vision-language models (VLMs) often encounter challenges such as insufficient capabilities of a single visual component and excessively long visual tokens. These issu…
Secrets of RLHF in Large Language Models Part II: Reward Modeling
Binghai Wang, Rui Zheng, Lu Chen +24
Reinforcement Learning from Human Feedback (RLHF) has become a crucial technology for aligning language models with human values and intentions, enabling models to produce more hel…
Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
Songyang Gao, Qiming Ge, Wei Shen +9
The success of AI assistants based on Language Models (LLMs) hinges on Reinforcement Learning from Human Feedback (RLHF) to comprehend and align with user intentions. However, trad…
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
Shihan Dou, Enyu Zhou, Yan Liu +13
Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks.…
Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback
Wei Shen, Rui Zheng, Wenyu Zhan +5
Reinforcement learning from human feedback serves as a crucial bridge, aligning large language models with human and societal values. This alignment requires a vast corpus of human…
Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation
Yikun Wang, Rui Zheng, Haoming Li +3
Customizing LLMs for a specific task involves separating high-quality responses from lower-quality ones. This skill can be developed using supervised fine-tuning with extensive hum…
Orthogonal Subspace Learning for Language Model Continual Learning
Xiao Wang, Tianze Chen, Qiming Ge +6
Benefiting from massive corpora and advanced hardware, large language models (LLMs) exhibit remarkable capabilities in language understanding and generation. However, their perform…