Reinforcing Thinking through Reasoning-Enhanced Reward Models

• URL: http://arxiv.org/abs/2501.01457v1
• Date: Tue, 31 Dec 2024 04:50:15 GMT
• Title: Reinforcing Thinking through Reasoning-Enhanced Reward Models
• Authors: Diji Yang, Linda Zeng, Kezhen Chen, Yi Zhang,
• Abstract summary: Large Language Models (LLMs) exhibit great potential in complex multi-step reasoning through inference-time thinking. LLMs struggle with deciding when to stop thinking due to limited self-awareness about their knowledge boundaries. This work addresses these challenges by distilling the LLM's own reasoning processes into synthetic behavioral data.
• Score: 6.636512424910708
• License:
• Abstract: Large Language Models (LLMs) exhibit great potential in complex multi-step reasoning through inference-time thinking but still struggle with deciding when to stop thinking due to limited self-awareness about their knowledge boundaries. While human preference alignment has shown extraordinary opportunities, expensive labeling challenges adherence to scaling law. Language model self-critique, as an alternative to using human-labeled reasoning data, is questioned with its inherited biases. This work addresses these challenges by distilling the LLM's own reasoning processes into synthetic behavioral data, eliminating the need for manual labeling of intermediate steps. Building on this concept, we propose Distillation-Reinforcement-Reasoning (DRR), a three-step framework that leverages the LLM's inherent behaviors as external feedback by first generating behavioral data using the Reasoner (LLM) to reflect its reasoning capabilities, then training a lightweight discriminative reward model (DM) on behavioral data, and finally deploying the DM at inference time to assist the Reasoner's decision-making. Experiments on multiple benchmarks show that the DRR framework outperforms self-critique approaches without relying on additional complex data annotation. Benefiting from lightweight design, ease of replication, and adaptability, DRR is applicable to a wide range of LLM-centric tasks.

Related papers

• Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling [87.17041933863041]
  We introduce a Response-conditioned Bradley-Terry (Rc-BT) model that enhances the reward model's capability in length bias mitigating and length instruction following. We also propose the Rc-DPO algorithm to leverage the Rc-BT model for direct policy optimization (DPO) of large language models.
  arXiv  Detail & Related papers  (2025-02-02T14:50:25Z)
• ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding [25.329712997545794]
  We propose Retrieval-Augmented Reasoning through Trustworthy Process Rewarding (ReARTeR) ReARTeR enhances RAG systems' reasoning capabilities through post-training and test-time scaling. Experimental results on multi-step reasoning benchmarks demonstrate significant improvements.
  arXiv  Detail & Related papers  (2025-01-14T05:56:26Z)
• Semi-Supervised Reward Modeling via Iterative Self-Training [52.48668920483908]
  We propose Semi-Supervised Reward Modeling (SSRM), an approach that enhances RM training using unlabeled data. We demonstrate that SSRM significantly improves reward models without incurring additional labeling costs. Overall, SSRM substantially reduces the dependency on large volumes of human-annotated data, thereby decreasing the overall cost and time involved in training effective reward models.
  arXiv  Detail & Related papers  (2024-09-10T22:57:58Z)
• Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling [9.44858963874474]
  Self-Consistency mitigates hallucinations in Large Language Models (LLMs) by sampling multiple reasoning paths. We introduce Reasoning-Aware Self-Consistency (RASC), a novel framework that enhances sampling efficiency and reasoning faithfulness.
  arXiv  Detail & Related papers  (2024-08-30T05:14:59Z)
• Making Large Language Models Better Planners with Reasoning-Decision Alignment [70.5381163219608]
  We motivate an end-to-end decision-making model based on multimodality-augmented LLM. We propose a reasoning-decision alignment constraint between the paired CoTs and planning results. We dub our proposed large language planners with reasoning-decision alignment as RDA-Driver.
  arXiv  Detail & Related papers  (2024-08-25T16:43:47Z)
• Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making [51.737762570776006]
  LLM-ACTR is a novel neuro-symbolic architecture that provides human-aligned and versatile decision-making. Our framework extracts and embeds knowledge of ACT-R's internal decision-making process as latent neural representations. Our experiments on novel Design for Manufacturing tasks show both improved task performance as well as improved grounded decision-making capability.
  arXiv  Detail & Related papers  (2024-08-17T11:49:53Z)
• Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models [42.17166746027585]
  We introduce a bidirectional weighted graph-based framework to learn factorized attributes and their interrelations within complex data. Specifically, we propose a $beta$-VAE based module to extract factors as the initial nodes of the graph. By integrating these complementary modules, our model successfully achieves fine-grained, practical and unsupervised disentanglement.
  arXiv  Detail & Related papers  (2024-07-26T15:32:21Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making. We present a process-based benchmark MR-Ben that demands a meta-reasoning skill. Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment [32.12998469814097]
  A novel causal prompting method based on front-door adjustment is proposed to effectively mitigate Large Language Models (LLMs) biases. Experimental results show that the proposed causal prompting approach achieves excellent performance across seven natural language processing datasets.
  arXiv  Detail & Related papers  (2024-03-05T07:47:34Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• Concise and Organized Perception Facilitates Reasoning in Large Language Models [32.71672086718057]
  We show that large language models (LLMs) exhibit failure patterns akin to human-like cognitive biases when dealing with disordered and irrelevant content in reasoning tasks. We propose a novel reasoning approach named Concise and Organized Perception (COP) COP carefully analyzes the given statements to identify the most pertinent information while eliminating redundancy efficiently.
  arXiv  Detail & Related papers  (2023-10-05T04:47:49Z)

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.