Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values

• URL: http://arxiv.org/abs/2502.13723v1
• Date: Wed, 19 Feb 2025 13:51:05 GMT
• Title: Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values
• Authors: Hongbo Zhang, Han Cui, Guangsheng Bao, Linyi Yang, Jun Wang, Yue Zhang,
• Abstract summary: Direct Value Optimization (DVO) is an innovative reinforcement learning framework for enhancing large language models in complex reasoning tasks. DVO utilizes value signals at individual reasoning steps, optimizing models via a mean squared error loss. Our empirical analysis on both mathematical and commonsense reasoning tasks shows that DVO consistently outperforms existing offline preference optimization techniques.
• Score: 31.415598465903884
• License:
• Abstract: We introduce Direct Value Optimization (DVO), an innovative reinforcement learning framework for enhancing large language models in complex reasoning tasks. Unlike traditional methods relying on preference labels, DVO utilizes value signals at individual reasoning steps, optimizing models via a mean squared error loss. The key benefit of DVO lies in its fine-grained supervision, circumventing the need for labor-intensive human annotations. Target values within the DVO are estimated using either Monte Carlo Tree Search or an outcome value model. Our empirical analysis on both mathematical and commonsense reasoning tasks shows that DVO consistently outperforms existing offline preference optimization techniques, even with fewer training steps. These findings underscore the importance of value signals in advancing reasoning capabilities and highlight DVO as a superior methodology under scenarios lacking explicit human preference information.

Related papers

• PILAF: Optimal Human Preference Sampling for Reward Modeling [14.336058926701432]
  We propose Policy-Interpolated Learning for Aligned Feedback (PILAF), a novel response sampling strategy for preference labeling. PILAF explicitly aligns preference learning with maximizing the underlying oracle reward.
  arXiv  Detail & Related papers  (2025-02-06T18:09:00Z)
• Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning [17.59802090014789]
  We introduce PrefVLM, a framework that integrates Vision-Language Models (VLMs) with selective human feedback. Our method leverages VLMs to generate initial preference labels, which are then filtered to identify uncertain cases for targeted human annotation. Experiments on Meta-World manipulation tasks demonstrate that PrefVLM achieves comparable or superior success rates to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-02-03T18:50:15Z)
• Reward-Guided Speculative Decoding for Efficient LLM Reasoning [80.55186052123196]
  We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs) RSD incorporates a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness. RSD delivers significant efficiency gains against decoding with the target model only, while achieving significant better accuracy than parallel decoding method on average.
  arXiv  Detail & Related papers  (2025-01-31T17:19:57Z)
• Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
  Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
  arXiv  Detail & Related papers  (2024-10-21T17:00:06Z)
• VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment [55.7956150385255]
  We investigate the efficacy of AI feedback to scale supervision for aligning vision-language models. We introduce VLFeedback, the first large-scale vision-language feedback dataset. We train Silkie, an LVLM fine-tuned via direct preference optimization on VLFeedback.
  arXiv  Detail & Related papers  (2024-10-12T07:56:47Z)
• Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
  We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-26T12:37:26Z)
• Silkie: Preference Distillation for Large Visual Language Models [56.10697821410489]
  This paper explores preference distillation for large vision language models (LVLMs) We first build a vision-language feedback dataset utilizing AI annotation. We adopt GPT-4V to assess the generated outputs regarding helpfulness, visual faithfulness, and ethical considerations. The resulting model Silkie, achieves 6.9% and 9.5% relative improvement on the MME benchmark regarding the perception and cognition capabilities.
  arXiv  Detail & Related papers  (2023-12-17T09:44:27Z)
• OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning [15.59540726867483]
  We argue that in guided decoding, assessing the potential of an incomplete reasoning path can be more advantageous than simply ensuring per-step correctness. Inspired by the findings that $textitoutcome supervision for guided decoding essentially acts as a value model, we propose Outcome-supervised Value Model (OVM) Our experiments on two multi-step mathematical reasoning datasets, GSM8K and Game of 24, demonstrate the superior performance of the OVM model.
  arXiv  Detail & Related papers  (2023-11-16T09:56:28Z)
• Domain Adaptation with Adversarial Training on Penultimate Activations [82.9977759320565]
  Enhancing model prediction confidence on unlabeled target data is an important objective in Unsupervised Domain Adaptation (UDA) We show that this strategy is more efficient and better correlated with the objective of boosting prediction confidence than adversarial training on input images or intermediate features.
  arXiv  Detail & Related papers  (2022-08-26T19:50:46Z)
• Provably Efficient Causal Reinforcement Learning with Confounded Observational Data [135.64775986546505]
  We study how to incorporate the dataset (observational data) collected offline, which is often abundantly available in practice, to improve the sample efficiency in the online setting. We propose the deconfounded optimistic value iteration (DOVI) algorithm, which incorporates the confounded observational data in a provably efficient manner.
  arXiv  Detail & Related papers  (2020-06-22T14:49:33Z)

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.