Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
- URL: http://arxiv.org/abs/2409.00162v1
- Date: Fri, 30 Aug 2024 16:14:35 GMT
- Title: Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
- Authors: Jiayi Zhou, Jiaming Ji, Juntao Dai, Yaodong Yang,
- Abstract summary: Reinforcement learning from human feedback (RLHF) aligns Large language models (LLMs) with human intentions and values.
Despite its effectiveness and popularity, RLHF is prone to biased local optimization.
We propose a novel textitsequence-to-sequence (seq2seq) reward modeling method.
- Score: 8.601283886845664
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs by training a reward model (RM) on human preferences and fine-tuning the LLMs to maximize RM feedback. Despite its effectiveness and popularity, RLHF is prone to biased local optimization. It means RM fails to provide feedback that accurately aligns with human preference, causing LLMs to explore unexpected generalizations, and failing to achieve alignment objectives. To mitigate this issue, we propose a novel \textit{sequence-to-sequence (seq2seq) reward modeling} method. Its key insight is that learning from language feedback rather than scalar feedback improves RLHF without additional annotations. We replaced the reward modeling target from binary maximum likelihood estimation (MLE) with sequence MLE. This method enables richer and fine-grained language feedback without additional annotations, models, or training stages. Our experiments demonstrated its effectiveness, specifically, reducing the refusal-to-response paradigm in single-turn safety dialogues and the long-response bias in text summarization tasks. We provide further analysis that seq2seq RM improves RLHF performance across 2B and 7B LLMs on 3 NLP tasks, achieving an average win rate of 76.9\%. We further show that seq2seq RM can still improve the performance of RLHF under out-of-distribution prompts.
Related papers
- Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model [96.20350225621813]
Reinforcement learning from human feedback (RLHF) has been widely adopted to align language models (LMs) with human preference.
In this paper, we seek to get the best of both by training and utilizing a segment-level reward model.
arXiv Detail & Related papers (2025-01-06T06:17:56Z) - Linear Probe Penalties Reduce LLM Sycophancy [3.6490659260835234]
Large language models (LLMs) are often sycophantic, prioritizing agreement with their users over accurate or objective statements.
This problematic behavior becomes more pronounced during reinforcement learning from human feedback (RLHF)
We develop a linear probing method to identify and penalize markers of sycophancy within the reward model, producing rewards that discourage sycophantic behavior.
arXiv Detail & Related papers (2024-12-01T21:11:28Z) - R3HF: Reward Redistribution for Enhancing Reinforcement Learning from Human Feedback [25.27230140274847]
Reinforcement learning from human feedback (RLHF) provides a paradigm for aligning large language models (LLMs) with human preferences.
This paper proposes a novel reward redistribution method called R3HF, which facilitates a more fine-grained, token-level reward allocation.
arXiv Detail & Related papers (2024-11-13T02:45:21Z) - Self-Evolved Reward Learning for LLMs [45.6910747154447]
Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences.
We propose Self-Evolved Reward Learning (SER), a novel approach where the RM generates additional training data to iteratively improve itself.
Our results demonstrate that even with limited human-annotated data, learning from self-feedback can robustly enhance RM performance.
arXiv Detail & Related papers (2024-11-01T07:29:03Z) - Post-hoc Reward Calibration: A Case Study on Length Bias [28.266675778940133]
Reward models (RMs) can develop biases by exploiting spurious correlations in their training data.
These biases can lead to incorrect output rankings, sub-optimal model evaluations, and the amplification of undesirable behaviours.
This paper addresses the challenge of correcting such biases without additional data and training.
arXiv Detail & Related papers (2024-09-25T22:30:42Z) - Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions.
Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
arXiv Detail & Related papers (2024-05-29T17:59:07Z) - Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning [49.87923965553233]
Reinforcement Learning can lead to reward over-optimization in large language models.
We introduce the Reward from Demonstration (RCfD) to recalibrate the reward objective.
We show that RCfD achieves comparable performance to carefully tuned baselines while mitigating ROO.
arXiv Detail & Related papers (2024-04-30T09:57:21Z) - ODIN: Disentangled Reward Mitigates Hacking in RLHF [127.35607931337019]
We study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback.
A well-formatted, verbose but less helpful response from the LLMs can often deceive LLMs or even human evaluators to achieve high scores.
Our approach almost eliminates the reward correlation with length, and improves the obtained policy by a significant margin.
arXiv Detail & Related papers (2024-02-11T22:40:12Z) - LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback [65.84061725174269]
Recent large language models (LLM) are leveraging human feedback to improve their generation quality.
We propose LLMRefine, an inference time optimization method to refine LLM's output.
We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization.
LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.
arXiv Detail & Related papers (2023-11-15T19:52:11Z) - Direct Preference Optimization: Your Language Model is Secretly a Reward Model [119.65409513119963]
We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form.
The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight.
Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
arXiv Detail & Related papers (2023-05-29T17:57:46Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.