English
Related papers

Related papers: Reward Collapse in Aligning Large Language Models

200 papers

Instruction tuning aligns the response of large language models (LLMs) with human preferences. Despite such efforts in human--LLM alignment, we find that instruction tuning does not always make LLMs human-like from a cognitive modeling…

Computation and Language · Computer Science 2024-04-16 Tatsuki Kuribayashi , Yohei Oseki , Timothy Baldwin

Large language models (LLMs) have become increasingly capable of following instructions and complex reasoning, making prompting a flexible interface for adapting models without parameter updates. Yet prompt design remains labor-intensive…

Computation and Language · Computer Science 2026-05-22 Farima Fatahi Bayat , Moin Aminnaseri , Pouya Pezeshkpour , Estevam Hruschka

Studies of reinforcement learning in humans and animals have demonstrated a preference for options that yielded relatively better outcomes in the past, even when those options are associated with lower absolute reward. The present study…

Computation and Language · Computer Science 2024-01-29 William M. Hayes , Nicolas Yax , Stefano Palminteri

Large Language Models (LLMs) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phenomenon known as "evaluation awareness." This discrepancy…

Computation and Language · Computer Science 2025-12-05 Lang Xiong , Nishant Bhargava , Jianhang Hong , Jeremy Chang , Haihao Liu , Vasu Sharma , Kevin Zhu

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human values. However, noisy preferences in human feedback can lead to reward misgeneralization - a phenomenon where reward models learn spurious…

Aligning large language models (LLMs) to human preferences is challenging in domains where preference data is unavailable. We address the problem of learning reward models for such target domains by leveraging feedback collected from…

Machine Learning · Computer Science 2025-01-03 David Wu , Sanjiban Choudhury

Despite recent progress, reinforcement learning (RL)-based fine-tuning of diffusion models often struggles with generalization, composability, and robustness against reward hacking. Recent studies have explored prompt refinement as a…

Machine Learning · Computer Science 2026-03-26 Suhyeon Lee , Jong Chul Ye

Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at scale, making it…

Computation and Language · Computer Science 2024-10-15 Zhaofeng Wu , Ananth Balashankar , Yoon Kim , Jacob Eisenstein , Ahmad Beirami

Within the scaling laws paradigm, which underpins the training of large neural networks like ChatGPT and Llama, we consider a supervised regression setting and establish the existance of a strong form of the model collapse phenomenon, a…

Machine Learning · Computer Science 2024-10-10 Elvis Dohmatob , Yunzhen Feng , Arjun Subramonian , Julia Kempe

Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting, dynamically improving its generative capabilities through…

Computation and Language · Computer Science 2025-08-11 Yidong Wang , Xin Wang , Cunxiang Wang , Junfeng Fang , Qiufeng Wang , Jianing Chu , Xuran Meng , Shuxun Yang , Libo Qin , Yue Zhang , Wei Ye , Shikun Zhang

Large language models (LLMs) demonstrate exceptional instruct-following ability to complete various downstream tasks. Although this impressive ability makes LLMs flexible task solvers, their performance in solving tasks also heavily relies…

Computation and Language · Computer Science 2024-06-03 Pengwei Zhan , Zhen Xu , Qian Tan , Jie Song , Ru Xie

Emotional intelligence significantly impacts our daily behaviors and interactions. Although Large Language Models (LLMs) are increasingly viewed as a stride toward artificial general intelligence, exhibiting impressive performance in…

Computation and Language · Computer Science 2023-11-14 Cheng Li , Jindong Wang , Yixuan Zhang , Kaijie Zhu , Wenxin Hou , Jianxun Lian , Fang Luo , Qiang Yang , Xing Xie

Emotional prompting - the use of specific emotional diction in prompt engineering - has shown increasing promise in improving large language model (LLM) performance, truthfulness, and responsibility. However these studies have been limited…

Machine Learning · Computer Science 2026-04-10 Ameen Patel , Felix Lee , Kyle Liang , Joseph Thomas

While reinforcement learning with verifiable rewards (RLVR) is effective to improve the reasoning ability of large language models (LLMs), its reliance on human-annotated labels leads to the scaling up dilemma, especially for complex tasks.…

Machine Learning · Computer Science 2026-03-17 Zizhuo Zhang , Jianing Zhu , Xinmu Ge , Zihua Zhao , Zhanke Zhou , Xuan Li , Xiao Feng , Jiangchao Yao , Bo Han

Large Language Models are typically trained with next-turn rewards, limiting their ability to optimize for long-term interaction. As a result, they often respond passively to ambiguous or open-ended user requests, failing to help users…

Artificial Intelligence · Computer Science 2025-07-31 Shirley Wu , Michel Galley , Baolin Peng , Hao Cheng , Gavin Li , Yao Dou , Weixin Cai , James Zou , Jure Leskovec , Jianfeng Gao

Large language models (LLMs) have demonstrated impressive success in a wide range of natural language processing (NLP) tasks due to their extensive general knowledge of the world. Recent works discovered that the performance of LLMs is…

Computation and Language · Computer Science 2024-11-25 Yuze Liu , Tingjie Liu , Tiehua Zhang , Youhua Xia , Jinze Wang , Zhishu Shen , Jiong Jin , Fei Richard Yu

Large Language Models (LLMs) have achieved remarkable progress in reasoning, yet sometimes produce responses that are suboptimal for users in tasks such as writing, information seeking, or providing practical guidance. Conventional…

Artificial Intelligence · Computer Science 2025-11-04 Siqi Zhu , David Zhang , Pedro Cisneros-Velarde , Jiaxuan You

Large Language Models, such as Generative Pre-trained Transformer 3 (aka. GPT-3), have been developed to understand language through the analysis of extensive text data, allowing them to identify patterns and connections between words.…

Computation and Language · Computer Science 2023-10-03 Baphumelele Masikisiki , Vukosi Marivate , Yvette Hlope

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality outputs. Our theoretical analysis shows that the key lies in…