Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding

• URL: http://arxiv.org/abs/2411.04282v2
• Date: Thu, 21 Nov 2024 20:29:09 GMT
• Title: Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
• Authors: Haolin Chen, Yihao Feng, Zuxin Liu, Weiran Yao, Akshara Prabhakar, Shelby Heinecke, Ricky Ho, Phil Mui, Silvio Savarese, Caiming Xiong, Huan Wang,
• Abstract summary: Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures.
• Score: 74.31981011985681
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at inference time, optimizing reasoning capabilities during training remains challenging. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution and optimizes it via variational approaches. LaTRO enables LLMs to concurrently improve both their reasoning process and ability to evaluate reasoning quality, without requiring external feedback or reward models. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures. On GSM8K, LaTRO improves zero-shot accuracy by an average of 12.5% over base models and 9.6% over supervised fine-tuning across Phi-3.5-mini, Mistral-7B, and Llama-3.1-8B. Our findings suggest that pre-trained LLMs possess latent reasoning capabilities that can be unlocked and enhanced through our proposed optimization approach in a self-improvement manner. The code of LaTRO is available at \url{https://github.com/SalesforceAIResearch/LaTRO}.

Related papers

• Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code [76.80306464249217]
  We propose TeaR, which aims at teaching LLMs to reason better.<n>TeaR leverages careful data curation and reinforcement learning to guide models in discovering optimal reasoning paths through code-related tasks.<n>We conduct extensive experiments using two base models and three long-CoT distillation models, with model sizes ranging from 1.5 billion to 32 billion parameters, and across 17 benchmarks spanning Math, Knowledge, Code, and Logical Reasoning.
  arXiv  Detail & Related papers  (2025-07-10T07:34:05Z)
• ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization [16.51303604678232]
  Reasoning Compression ThroUgh Stepwise Trials (ReCUT) is a novel method aimed at balancing the accuracy and length of reasoning trajectory.<n> Experimental results across multiple math reasoning datasets and backbone models demonstrate that ReCUT significantly reduces reasoning lengths by approximately 30-50%.
  arXiv  Detail & Related papers  (2025-06-12T15:43:01Z)
• Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem [53.3188041952701]
  We show that Critique Fine-Tuning (CFT) on only one problem can effectively unleash the reasoning potential of LLMs.<n>With just 5 GPU hours of training, Qwen-Math-7B-CFT show an average improvement of 15% on six math benchmarks and 16% on three logic reasoning benchmarks.<n>Results are comparable to or even surpass the results from RL with 20x less compute.
  arXiv  Detail & Related papers  (2025-06-03T18:35:52Z)
• RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning [10.987902254146219]
  We train a lightweight navigator model with reinforcement learning (RL) to adaptively enhance reasoning at inference time.<n>With less than 3K parameters, our RL navigator is able to make sub-10B LLMs comparable to 100B-scale counterparts.
  arXiv  Detail & Related papers  (2025-05-20T09:43:33Z)
• S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
  We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference. Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
  arXiv  Detail & Related papers  (2025-02-18T13:40:22Z)
• SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs [48.28847964704554]
  Chain-of-Thought (CoT) reasoning enables Large Language Models (LLMs) to solve complex reasoning tasks.<n>We propose a novel approach for continuous-space reasoning that does not require modifying the LLM.
  arXiv  Detail & Related papers  (2025-02-17T18:52:29Z)
• Large Language Diffusion Models [77.02553707673418]
  Autoregressive models (ARMs) are widely regarded as the cornerstone of large language models (LLMs) We introduce LLaDA, a diffusion model trained from scratch under the pre-training and supervised fine-tuning paradigm. Across extensive benchmarks, LLaDA demonstrates strong scalability, outperforming our self-constructed ARM baselines.
  arXiv  Detail & Related papers  (2025-02-14T08:23:51Z)
• On the Emergence of Thinking in LLMs I: Searching for the Right Intuition [34.32871896067864]
  We propose a post-training framework called Reinforcement Learning via Self-Play (RLSP) RLSP involves three steps: supervised fine-tuning with human or synthetic demonstrations of the reasoning process, using an exploration reward signal to encourage diverse and efficient reasoning behaviors, and RL training with an outcome verifier to ensure correctness while preventing reward hacking. Empirical studies in the math domain show that RLSP improves reasoning.
  arXiv  Detail & Related papers  (2025-02-10T18:52:04Z)
• LLM2: Let Large Language Models Harness System 2 Reasoning [65.89293674479907]
  Large language models (LLMs) have exhibited impressive capabilities across a myriad of tasks, yet they occasionally yield undesirable outputs. We introduce LLM2, a novel framework that combines an LLM with a process-based verifier. LLMs2 is responsible for generating plausible candidates, while the verifier provides timely process-based feedback to distinguish desirable and undesirable outputs.
  arXiv  Detail & Related papers  (2024-12-29T06:32:36Z)
• Learning to Reason via Self-Iterative Process Feedback for Small Language Models [5.3831551965806534]
  Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs) This study enables SLMs to learn to reason from self-iterative feedback.
  arXiv  Detail & Related papers  (2024-12-11T14:05:04Z)
• LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints [86.59857711385833]
  We introduce RealInstruct, the first benchmark designed to evaluate LLMs' ability to follow real-world multi-constrained instructions. To address the performance gap between open-source and proprietary models, we propose the Decompose, Critique and Refine (DeCRIM) self-correction pipeline. Our results show that DeCRIM improves Mistral's performance by 7.3% on RealInstruct and 8.0% on IFEval even with weak feedback.
  arXiv  Detail & Related papers  (2024-10-09T01:25:10Z)
• Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter? [36.14795256060537]
  We develop GridPuzzle, an evaluation dataset comprising 274 grid-based puzzles with different complexities. Second, we propose a new error taxonomy derived from manual analysis of reasoning chains from LLMs including GPT-4, Claude-3, Gemini, Mistral, and Llama-2. Third, we develop an LLM-based framework for large-scale subjective evaluation (i.e., identifying errors) and an objective metric, PuzzleEval, to evaluate the correctness of reasoning chains.
  arXiv  Detail & Related papers  (2024-07-20T07:43:07Z)
• Steamroller Problems: An Evaluation of LLM Reasoning Capability with Automated Theorem Prover Strategies [0.18416014644193066]
  We evaluate the performance of GPT4, GPT3.5 Turbo and Google's recent Gemini model on problems from a steamroller domain. We found that the models' performance when using the ATP reasoning strategies was comparable to one-shot chain of thought.
  arXiv  Detail & Related papers  (2024-07-17T22:49:23Z)
• PORT: Preference Optimization on Reasoning Traces [1.7292887546437081]
  This paper proposes using preference optimization methods on Chain-of-Thought steps in order to improve the reasoning performances of language models. Our approach leads to increased accuracy on the GSM8K, AQuA-RAT, and ARC benchmarks for Falcon2-11B and Mistral-7B.
  arXiv  Detail & Related papers  (2024-06-23T09:51:06Z)
• 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)
• Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration [70.09561665520043]
  We propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans. We provide theoretical analysis by extending advantage-weighted regression in reinforcement learning to multi-agent systems. Experiments on Over-AI and a difficult variant of RoCoBench show that ReAd surpasses baselines in success rate, and also significantly decreases the interaction steps of agents.
  arXiv  Detail & Related papers  (2024-05-23T08:33:19Z)
• Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards [42.065997425172974]
  Training on large amounts of rationales (i.e., CoT Fine-tuning) is effective at improving the reasoning capabilities of large language models (LLMs) We propose Self-Explore, where the LLM is tasked to explore the first wrong step within the rationale and use such signals as fine-grained rewards for further improvement. On the GSM8K and MATH test set, Self-Explore achieves 11.57% and 2.89% improvement on average across three LLMs compared to supervised fine-tuning (SFT)
  arXiv  Detail & Related papers  (2024-04-16T07:30:11Z)
• RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought [56.558892336235914]
  Reversing Chain-of-Thought (RCoT) is a novel method to improve large language models' reasoning abilities. RCoT automatically detects and rectifys factual inconsistency in generated solutions. We show that manually written fine-grained feedback can dramatically improve LLMs' reasoning abilities.
  arXiv  Detail & Related papers  (2023-05-19T08:02:52Z)
• SatLM: Satisfiability-Aided Language Models Using Declarative Prompting [68.40726892904286]
  We propose a new satisfiability-aided language modeling (SatLM) approach for improving the reasoning capabilities of large language models (LLMs) We use an LLM to generate a declarative task specification rather than an imperative program and leverage an off-the-shelf automated theorem prover to derive the final answer. We evaluate SATLM on 8 different datasets and show that it consistently outperforms program-aided LMs in the imperative paradigm.
  arXiv  Detail & Related papers  (2023-05-16T17:55:51Z)
• Large Language Models Can Self-Improve [34.78624270280148]
  We use a pre-trained LLM to generate "high-confidence" rationale-augmented answers for unlabeled questions. We show that our approach achieves state-of-the-art-level performance, without any ground truth label.
  arXiv  Detail & Related papers  (2022-10-20T21:53:54Z)

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.