Pith. sign in

REVIEW 3 cited by

Advancing Process Verification for Large Language Models via Tree-Based Preference Learning

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

arxiv 2407.00390 v1 pith:4EXZA6A3 submitted 2024-06-29 cs.CL

classification cs.CL
keywords reasoningpreferencelearningstep-leveltree-plvevaluationexistingfeedback
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large Language Models (LLMs) have demonstrated remarkable potential in handling complex reasoning tasks by generating step-by-step rationales.Some methods have proven effective in boosting accuracy by introducing extra verifiers to assess these paths. However, existing verifiers, typically trained on binary-labeled reasoning paths, fail to fully utilize the relative merits of intermediate steps, thereby limiting the effectiveness of the feedback provided. To overcome this limitation, we propose Tree-based Preference Learning Verifier (Tree-PLV), a novel approach that constructs reasoning trees via a best-first search algorithm and collects step-level paired data for preference training. Compared to traditional binary classification, step-level preferences more finely capture the nuances between reasoning steps, allowing for a more precise evaluation of the complete reasoning path. We empirically evaluate Tree-PLV across a range of arithmetic and commonsense reasoning tasks, where it significantly outperforms existing benchmarks. For instance, Tree-PLV achieved substantial performance gains over the Mistral-7B self-consistency baseline on GSM8K (67.55% to 82.79%), MATH (17.00% to 26.80%), CSQA (68.14% to 72.97%), and StrategyQA (82.86% to 83.25%).Additionally, our study explores the appropriate granularity for applying preference learning, revealing that step-level guidance provides feedback that better aligns with the evaluation of the reasoning process.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation

    cs.CL 2024-12 conditional novelty 6.0 of 10

    A tree-based, inference-only framework combining execution metrics with LLM self-critique improves code generation correctness and efficiency across models and benchmarks.

  2. GenCLS++: Pushing the Boundaries of Generative Classification in LLMs Through Comprehensive SFT and RL Studies Across Diverse Datasets

    cs.CL 2025-04 conditional novelty 5.0 of 10

    SFT plus RL with post-hoc selection of the best training and inference prompts improves generative text classification accuracy by about 3.5% relative to a naive SFT baseline.

  3. LLMSR@XLLM25: An Empirical Study of LLM for Structural Reasoning

    cs.CL 2025-05 conditional novelty 4.0 of 10

    A few-shot, untuned Meta-Llama-3-8B-Instruct system with regex post-processing ranks 5th on the LLMSR@XLLM25 structural reasoning shared task.

Pith tools