English
Related papers

Related papers: Reward Collapse in Aligning Large Language Models

200 papers

Reward hacking--where agents exploit flaws in imperfect reward functions rather than performing tasks as intended--poses risks for AI alignment. Reward hacking has been observed in real training runs, with coding agents learning to…

Artificial Intelligence · Computer Science 2025-08-26 Mia Taylor , James Chua , Jan Betley , Johannes Treutlein , Owain Evans

The reasoning abilities of Large Language Models (LLMs) remain a topic of debate. Some methods such as ReAct-based prompting, have gained popularity for claiming to enhance sequential decision-making abilities of agentic LLMs. However, it…

Artificial Intelligence · Computer Science 2024-05-24 Mudit Verma , Siddhant Bhambri , Subbarao Kambhampati

The inherent uncertainty in the environmental transition model of Reinforcement Learning (RL) necessitates a delicate balance between exploration and exploitation. This balance is crucial for optimizing computational resources to accurately…

Machine Learning · Computer Science 2025-05-21 Yongxin Deng , Xihe Qiu , Jue Chen , Xiaoyu Tan

Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domains. Despite its empirical success, it remains unclear whether…

Machine Learning · Computer Science 2026-01-27 Mingyuan Fan , Weiguang Han , Daixin Wang , Cen Chen , Zhiqiang Zhang , Jun Zhou

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that…

Computation and Language · Computer Science 2025-03-04 Jixuan Leng , Chengsong Huang , Banghua Zhu , Jiaxin Huang

Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine-tuning; on the…

Computation and Language · Computer Science 2025-09-30 Qingjie Zhang , Haoting Qian , Zhicong Huang , Cheng Hong , Minlie Huang , Ke Xu , Chao Zhang , Han Qiu

The remarkable capabilities and easy accessibility of large language models (LLMs) have significantly increased societal risks (e.g., fake news generation), necessitating the development of LLM-generated text (LGT) detection methods for…

Machine Learning · Computer Science 2024-11-08 Hyunseok Lee , Jihoon Tack , Jinwoo Shin

Large language models (LLMs) have revolutionized zero-shot task performance, mitigating the need for task-specific annotations while enhancing task generalizability. Despite its advancements, current methods using trigger phrases such as…

Computation and Language · Computer Science 2024-06-13 Saurabh Srivastava , Chengyue Huang , Weiguo Fan , Ziyu Yao

Modern large language models (LLMs) are optimized for human-aligned responses using Reinforcement Learning from Human Feedback (RLHF). However, existing RLHF approaches assume a universal preference model and fail to account for individual…

Machine Learning · Computer Science 2025-03-11 Idan Shenfeld , Felix Faltings , Pulkit Agrawal , Aldo Pacchiano

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

Computation and Language · Computer Science 2025-02-28 Yudi Zhang , Lu Wang , Meng Fang , Yali Du , Chenghua Huang , Jun Wang , Qingwei Lin , Mykola Pechenizkiy , Dongmei Zhang , Saravan Rajmohan , Qi Zhang

Learning from human feedback via proxy reward modeling has been studied to align Large Language Models (LLMs) with human values. However, achieving reliable training through that proxy reward model (RM) is not a trivial problem, and its…

Machine Learning · Computer Science 2024-10-08 Sungdong Kim , Minjoon Seo

Large language models (LLMs) have achieved remarkable success in a wide range of natural language processing tasks and can be adapted through prompting. However, they remain suboptimal in multi-turn interactions, often relying on incorrect…

LLM-based Automatic Prompt Optimization, which typically utilizes LLMs as Prompt Optimizers to self-reflect and refine prompts, has shown promising performance in recent studies. Despite the success, the underlying mechanism of this…

Computation and Language · Computer Science 2024-02-06 Ruotian Ma , Xiaolei Wang , Xin Zhou , Jian Li , Nan Du , Tao Gui , Qi Zhang , Xuanjing Huang

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…

Computation and Language · Computer Science 2026-03-06 Biao Liu , Ning Xu , Junming Yang , Hao Xu , Xin Geng

This paper presents an integrated systematic study of the performance of large language models (LLMs), specifically ChatGPT, for automatically formulating and solving Stochastic Optimization (SO) problems from natural language descriptions.…

Artificial Intelligence · Computer Science 2026-01-15 Amirreza Talebi

Large language models (LLMs) have shown impressive success in various applications. However, these models are often not well aligned with human intents, which calls for additional treatments on them; that is, the alignment problem. To make…

Computation and Language · Computer Science 2024-06-24 Jiale Cheng , Xiao Liu , Kehan Zheng , Pei Ke , Hongning Wang , Yuxiao Dong , Jie Tang , Minlie Huang

Large language models (LLMs) hold potential for mental healthcare applications, particularly in cognitive behavioral therapy (CBT)-based counseling, where reward models play a critical role in aligning LLMs with preferred therapeutic…

Databases · Computer Science 2026-03-13 Yougen Zhou , Qin Chen , Ningning Zhou , Jie Zhou , Liang He

We investigated the capability of the GPT-3.5 large language model (LLM) to operationalize natural language descriptions of cooperative, competitive, altruistic, and self-interested behavior in two social dilemmas: the repeated Prisoners…

Computer Science and Game Theory · Computer Science 2024-07-02 Steve Phelps , Yvan I. Russell

Large language models have demonstrated surprising ability to perform in-context learning, i.e., these models can be directly applied to solve numerous downstream tasks by conditioning on a prompt constructed by a few input-output examples.…

Computation and Language · Computer Science 2023-04-03 Huan Ma , Changqing Zhang , Yatao Bian , Lemao Liu , Zhirui Zhang , Peilin Zhao , Shu Zhang , Huazhu Fu , Qinghua Hu , Bingzhe Wu

Finetuning language models with reinforcement learning (RL), e.g. from human feedback (HF), is a prominent method for alignment. But optimizing against a reward model can improve on reward while degrading performance in other areas, a…

Computation and Language · Computer Science 2023-12-14 Michael Noukhovitch , Samuel Lavoie , Florian Strub , Aaron Courville
‹ Prev 1 8 9 10 Next ›