English
Related papers

Related papers: Spontaneous Reward Hacking in Iterative Self-Refin…

200 papers

There has been considerable divergence of opinion on the reasoning abilities of Large Language Models (LLMs). While the initial optimism that reasoning might emerge automatically with scale has been tempered thanks to a slew of…

Artificial Intelligence · Computer Science 2024-08-06 Kaya Stechly , Karthik Valmeekam , Subbarao Kambhampati

With the advancement in generative language models, the selection of prompts has gained significant attention in recent years. A prompt is an instruction or description provided by the user, serving as a guide for the generative language…

Machine Learning · Statistics 2024-05-21 Haoting Zhang , Jinghai He , Rhonda Righter , Zeyu Zheng

The success of reinforcement learning from human feedback (RLHF) in language model alignment is strongly dependent on the quality of the underlying reward model. In this paper, we present a novel approach to improve reward model quality by…

Computation and Language · Computer Science 2024-10-28 Alizée Pace , Jonathan Mallinson , Eric Malmi , Sebastian Krause , Aliaksei Severyn

Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models. For complex tasks such as image editing, reward models are required to capture global…

Layout design, such as user interface or graphical layout in general, is fundamentally an iterative revision process. Through revising a design repeatedly, the designer converges on an ideal layout. In this paper, we investigate how…

Human-Computer Interaction · Computer Science 2024-06-28 Tao Li , Chin-Yi Cheng , Amber Xie , Gang Li , Yang Li

Autonomous agents optimize the reward function we give them. What they don't know is how hard it is for us to design a reward function that actually captures what we want. When designing the reward, we might think of some specific training…

Artificial Intelligence · Computer Science 2020-10-08 Dylan Hadfield-Menell , Smitha Milli , Pieter Abbeel , Stuart Russell , Anca Dragan

Games are challenging for Reinforcement Learning~(RL) agents due to their reward-sparsity, as rewards are only obtainable after long sequences of deliberate actions. Intrinsic Motivation~(IM) methods -- which introduce exploration rewards…

Artificial Intelligence · Computer Science 2025-07-29 Leonardo Villalobos-Arias , Grant Forbes , Jianxun Wang , David L Roberts , Arnav Jhala

Reward models (RMs) used in reinforcement learning from human feedback (RLHF) are vulnerable to reward hacking: as the policy maximizes a learned proxy reward, true quality plateaus or degrades. We make the assumption that reward hacking is…

Machine Learning · Computer Science 2026-04-06 Shinnosuke Ono , Johannes Ackermann , Soichiro Nishimori , Takashi Ishida , Masashi Sugiyama

Human feedback has become the de facto standard for evaluating the performance of Large Language Models, and is increasingly being used as a training objective. However, it is not clear which properties of a generated output this single…

Computation and Language · Computer Science 2024-01-17 Tom Hosking , Phil Blunsom , Max Bartolo

In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming can range from simple behaviors like sycophancy to…

Reinforcement Learning from Human Feedback significantly enhances Natural Language Processing by aligning language models with human expectations. A critical factor in this alignment is the strength of reward models used during training.…

Computation and Language · Computer Science 2024-10-17 Yanjun Chen , Dawei Zhu , Yirong Sun , Xinghao Chen , Wei Zhang , Xiaoyu Shen

Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e.g., chain-of-thought prompting. However, these intermediate inference steps may be inappropriate…

Computation and Language · Computer Science 2024-02-06 Debjit Paul , Mete Ismayilzada , Maxime Peyrard , Beatriz Borges , Antoine Bosselut , Robert West , Boi Faltings

To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update…

Automatic grading models are valued for the time and effort saved during the instruction of large student bodies. Especially with the increasing digitization of education and interest in large-scale standardized testing, the popularity of…

Computation and Language · Computer Science 2022-11-21 Anna Filighera , Sebastian Ochs , Tim Steuer , Thomas Tregel

We lack a systematic understanding of the effects of fine-tuning (via methods such as instruction-tuning or reinforcement learning from human feedback), particularly on tasks outside the narrow fine-tuning distribution. In a simplified…

Computation and Language · Computer Science 2024-04-16 Suhas Kotha , Jacob Mitchell Springer , Aditi Raghunathan

In this paper, we propose a simple yet efficient approach based on prompt engineering that leverages the large language model itself to optimize its answers without relying on auxiliary models. We introduce an iterative self-evaluating…

Computation and Language · Computer Science 2023-05-09 Tianqiang Yan , Tiansheng Xu

Iterative retrieval refers to the process in which the model continuously queries the retriever during generation to enhance the relevance of the retrieved knowledge, thereby improving the performance of Retrieval-Augmented Generation…

Computation and Language · Computer Science 2024-12-02 Tian Yu , Shaolei Zhang , Yang Feng

Many recent advances in natural language generation have been fueled by training large language models on internet-scale data. However, this paradigm can lead to models that generate toxic, inaccurate, and unhelpful content, and automatic…

We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive learning from language assumes a particular form of input (e.g.,…

Artificial Intelligence · Computer Science 2021-07-06 Theodore R. Sumers , Mark K. Ho , Robert D. Hawkins , Karthik Narasimhan , Thomas L. Griffiths

We address the problem of reward hacking, where maximising a proxy reward does not necessarily increase the true reward. This is a key concern for Large Language Models (LLMs), as they are often fine-tuned on human preferences that may not…

‹ Prev 1 4 5 6 7 8 10 Next ›