Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective
A large number of heuristics have been proposed to optimize the reinforcement fine-tuning of LLMs. However, inconsistent claims are made from time to time, making this area elusive. Reflecting on this situation, two fundamental questions still lack a clear understanding: 1) what is the role of each optimizing choice? 2) which ones are the bottlenecks? This paper aims to shed light on them, and it faces the challenge of several entangled confounding factors in the fine-tuning process. To tackle this challenge, we propose a bottom-up experiment pipeline. The bottom layer is composed of a minimalist configuration: one training data, one rollout per round and the reward directly serve as the learning signal without advantage function design. This minimalist configuration connects to multi-armed bandit learning with extremely large discrete action space, which offers theories to corroborate the experiment findings. The up procedure of the experiment pipeline expanding the minimalist configuration layer by layer, examining the role of each design choice. Experimental results on three LLMs and two reasoning datasets not only reveal new understanding of the design choice but also yield essential insights to shape the area.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning
The alignment tuning process of large language models (LLMs) typically involves instruction learning through supervised fine-tuning (SFT) and preference tuning via reinforcement learning from human feedback (RLHF). A rec…
In-Context LearningRethinking with Retrieval: Faithful Large Language Model Inference
Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the nee…
Language ModelingLanguage ModellingLarge Language Modelmodel+2REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding
Self-reflection mechanisms that rely on purely text-based rethinking processes perform well in most multimodal tasks. However, when directly applied to long-form video understanding scenarios, they exhibit clear limitati…
Reinforcement LearningRethinking Post-Training Recipes for Multimodal Time-Series Forecasting
Time-Series Foundation Models (TSFMs) excel at zero-shot unimodal forecasting using numerical data, but unlike LLMs they cannot consume multimodal, non-numerical context that often shape real-world trajectories. In this …
Reinforcement LearningVideo-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning
Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and finetuning remain significant challenges. These methods often rely on large-scale supervised fi…
Reinforcement Learning (RL)