REVIEW 6 cited by
Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 6 Pith papers
-
Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning?
CreditCardQA shows LLMs err mainly on credit-card contractual conditions and comparisons, not arithmetic, with Program-of-Thought narrowing open–closed model gaps.
-
VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
A vision-expert-filtered, chain-of-thought-guided, iteratively fine-tuned reward model boosts a compact 7B model's ability to judge vision-language responses, especially detecting hallucinations.
-
One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL
A pipeline converts short-CoT LLM outputs into o1-style long chain-of-thought rationales using 1K seed reasoning flows, and SFT on the resulting dataset improves downstream RLVR cold-start.
-
VerifyLLM: LLM-Based Pre-Execution Task Plan Verification for Robots
An LLM plus LTL-based verification module that reorders, inserts, and removes steps in household robot plans, reporting reduced ordering errors but with weak experimental support.
-
Trustworthy AI in Digital Health: A Comprehensive Review of Robustness and Explainability
A survey of robustness and explainability methods for digital health AI, proposing a taxonomy and illustrating known XAI tools, without new empirical or theoretical results.
-
DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning
Multi-agent reasoning gains can be written as coverage × selection accuracy, which is a conditioning identity rather than a new decomposition; the PRISM system still shows moderate benchmark gains.
Discussion (0). Sign in to comment.