Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
- URL: http://arxiv.org/abs/2410.05318v1
- Date: Sat, 5 Oct 2024 05:21:48 GMT
- Title: Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
- Authors: Zhenwen Liang, Ye Liu, Tong Niu, Xiangliang Zhang, Yingbo Zhou, Semih Yavuz,
- Abstract summary: Large language models (LLMs) struggle with consistent and accurate reasoning.
LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors.
We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
- Score: 52.095460362197336
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Despite significant advancements in the general capability of large language models (LLMs), they continue to struggle with consistent and accurate reasoning, especially in complex tasks such as mathematical and code reasoning. One key limitation is that LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors, which hampers their ability to reliably verify and rank outputs. To address this, we scale up the inference-time computation by generating multiple reasoning paths and employing verifiers to assess and rank the generated outputs by correctness. To facilitate this, we introduce a comprehensive dataset consisting of correct and incorrect solutions for math and code tasks, generated by multiple LLMs. This diverse set of solutions enables verifiers to more effectively distinguish and rank correct answers from erroneous outputs. The training methods for building verifiers were selected based on an extensive comparison of existing approaches. Moreover, to leverage the unique strengths of different reasoning strategies, we propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification. CoT provides a clear, step-by-step reasoning process that enhances interpretability, while PoT, being executable, offers a precise and error-sensitive validation mechanism. By taking both of their strengths, our approach significantly improves the accuracy and reliability of reasoning verification. Our verifiers, Math-Rev and Code-Rev, demonstrate substantial performance gains to existing LLMs, achieving state-of-the-art results on benchmarks such as GSM8k and MATH and even outperforming GPT-4o with Qwen-72B-Instruct as the reasoner.
Related papers
- CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
arXiv Detail & Related papers (2025-08-05T17:55:24Z) - Code Execution as Grounded Supervision for LLM Reasoning [36.97199200274124]
Training large language models with chain-of-thought (CoT) supervision has proven effective for enhancing their reasoning abilities.<n>We propose a scalable method for generating a high-quality CoT supervision dataset by leveraging the determinism of program execution.<n>Our approach extracts verifiable, step-by-step reasoning traces from code execution and transforms them into a natural language CoT reasoning.
arXiv Detail & Related papers (2025-06-12T04:36:57Z) - Right Is Not Enough: The Pitfalls of Outcome Supervision in Training LLMs for Math Reasoning [35.142294794883455]
We introduce MathOlympiadEval, a new dataset with fine-grained annotations, which reveals a significant gap between LLMs' answer correctness and their low process correctness.<n>Existing automated methods like LLM-as-a-judge struggle to reliably detect these reasoning flaws.<n>We propose ParaStepVerifier, a novel methodology for meticulous, step-by-step verification of mathematical solutions.
arXiv Detail & Related papers (2025-06-07T17:54:56Z) - Search-Based Correction of Reasoning Chains for Language Models [72.61861891295302]
Chain-of-Thought (CoT) reasoning has advanced the capabilities and transparency of language models (LMs)<n>We introduce a new self-correction framework that augments each reasoning step in a CoT with a latent variable indicating its veracity.<n>We also introduce Search Corrector, a discrete search algorithm over-valued veracity assignments.
arXiv Detail & Related papers (2025-05-17T04:16:36Z) - Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs [45.33160999781074]
Chain-of-Thought (CoT) reasoning has been demonstrated as an effective technique for improving the problem-solving capabilities of large language models (LLMs)
We introduce UnCert-CoT, an approach designed to enhance code generation by incorporating an uncertainty-aware CoT reasoning mechanism.
arXiv Detail & Related papers (2025-03-19T15:40:45Z) - Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning [40.069109287947875]
We propose a novel reasoning framework called Forest-of-Thought (FoT)
FoT integrates multiple reasoning trees to leverage collective decision-making for solving complex logical problems.
FoT employs sparse activation strategies to select the most relevant reasoning paths, improving both efficiency and accuracy.
arXiv Detail & Related papers (2024-12-12T09:01:18Z) - Think Beyond Size: Adaptive Prompting for More Effective Reasoning [0.0]
We introduce Adaptive Prompting, a dynamic and iterative framework designed to enhance reasoning by incorporating real-time adjustments to prompt structures and validation mechanisms.
Results demonstrate that Adaptive Prompting significantly improves performance on diverse reasoning benchmarks, including arithmetic reasoning (GSM8K, MultiArithm), logical reasoning and commonsense tasks.
Our approach enables smaller models to achieve competitive performance with larger counterparts, such as GPT-4, while maintaining computational efficiency.
arXiv Detail & Related papers (2024-10-10T17:14:36Z) - Subtle Errors Matter: Preference Learning via Error-injected Self-editing [59.405145971637204]
We propose a novel preference learning framework called eRror-Injected Self-Editing (RISE)
RISE injects predefined subtle errors into pivotal tokens in reasoning or steps to construct hard pairs for error mitigation.
Experiments validate the effectiveness of RISE, with preference learning on Qwen2-7B-Instruct yielding notable improvements of 3.0% on GSM8K and 7.9% on MATH with only 4.5K training samples.
arXiv Detail & Related papers (2024-10-09T07:43:38Z) - S$^3$c-Math: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners [23.713779973116733]
Self-correction is a method that can stimulate the potential reasoning abilities of large language models (LLMs)
We propose S$3$c-Math, which are able to perform Spontaneous Step-level Self-correction for Mathematical reasoning.
arXiv Detail & Related papers (2024-09-03T01:40:21Z) - Generative Verifiers: Reward Modeling as Next-Token Prediction [29.543787728397643]
Verifiers or reward models are often used to enhance the reasoning performance of large language models (LLMs)
We propose training verifiers using the ubiquitous next-token prediction objective, jointly on verification and solution generation.
We demonstrate that GenRM outperforms discriminative, DPO verifiers, and LLM-as-a-Judge.
arXiv Detail & Related papers (2024-08-27T17:57:45Z) - CoT Rerailer: Enhancing the Reliability of Large Language Models in Complex Reasoning Tasks through Error Detection and Correction [9.44858963874474]
Chain-of-Thought (CoT) prompting enhances Large Language Models (LLMs) complex reasoning abilities.
We propose the CoT Rerailer to address these challenges, employing self-consistency and multi-agent debate systems.
We demonstrate the effectiveness of our approach across diverse question-answering datasets in various knowledge domains.
arXiv Detail & Related papers (2024-08-25T21:20:17Z) - Prover-Verifier Games improve legibility of LLM outputs [12.532113917099885]
We study legibility in the context of solving grade-school math problems.
We propose a training algorithm inspired by Prover-Verifier Game from Anil et al.
We show that legibility training transfers to time-constrained humans tasked with verifying solution correctness.
arXiv Detail & Related papers (2024-07-18T16:58:18Z) - AssertionBench: A Benchmark to Evaluate Large-Language Models for Assertion Generation [6.3585378855805725]
We present a novel benchmark to evaluate Large-Language Models' effectiveness for assertion generation.
AssertioBench contains 100 curated Verilog hardware designs from OpenCores and formally verified assertions for each design generated from GoldMine and HARM.
arXiv Detail & Related papers (2024-06-26T14:47:28Z) - LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback [71.95402654982095]
We propose Math-Minos, a natural language feedback-enhanced verifier.
Our experiments reveal that a small set of natural language feedback can significantly boost the performance of the verifier.
arXiv Detail & Related papers (2024-06-20T06:42:27Z) - MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time [51.5039731721706]
MindStar is a purely inference-based searching method for large language models.
It formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths.
It significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1.
arXiv Detail & Related papers (2024-05-25T15:07:33Z) - Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems [50.76385564061713]
Chain-of-Thought (CoT) prompting has enhanced the performance of Large Language Models (LLMs) across various reasoning tasks.
CoT usually suffers from three pitfalls: semantic misunderstanding errors, calculation errors, and step-missing errors.
We propose Deeply Understanding the Problems (DUP) to improve the LLMs' math problem-solving ability by addressing semantic misunderstanding errors.
arXiv Detail & Related papers (2024-04-23T12:16:05Z) - 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)
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.