Pith. sign in

REVIEW 5 cited by

Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework

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 2305.03268 v1 pith:NJSRI4UY submitted 2023-05-05 cs.CL

classification cs.CL
keywords reasoningtasksframeworkchain-of-thoughtchainsfactualitygeneratingperformance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As large language models (LLMs) have become the norm in NLP, demonstrating good performance in generation and reasoning tasks, one of its most fatal disadvantages is the lack of factual correctness. Generating unfactual texts not only leads to lower performances but also degrades the trust and validity of their applications. Chain-of-Thought (CoT) prompting improves trust and model performance on complex reasoning tasks by generating interpretable reasoning chains, but still suffers from factuality concerns in knowledge-intensive tasks. In this paper, we propose the Verify-and-Edit framework for CoT prompting, which seeks to increase prediction factuality by post-editing reasoning chains according to external knowledge. Building on top of GPT-3, our framework lead to accuracy improvements in multiple open-domain question-answering tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions

    cs.CR 2026-07 conditional novelty 6.0 of 10

    Across 74 OSINT/CTI AI studies, hallucination is widely named but end-to-end measured in only one non-reproducible system, so a human–AI co-pilot is the most defensible near-term architecture.

  2. Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains

    cs.CL 2025-06 conditional novelty 6.0 of 10

    LLM reasoning can be scored separately for knowledge and step-by-step information gain, and doing so shows SFT and RL affect these two capacities differently across medicine and math.

  3. Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Temporal Grounding

    cs.CV 2025-08 conditional novelty 5.0 of 10

    Rollout-averaged pseudo labels with variance-based confidence weighting let a GRPO-trained temporal grounding model adapt to an unlabelled target domain from only 100-200 videos.

  4. Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers

    cs.CL 2025-05 conditional novelty 5.0 of 10

    EXSEARCH trains LLMs for agentic search by treating search trajectories as latent variables and optimizing a weighted likelihood via expectation-maximization, yielding gains on NQ, HotpotQA, MuSiQue, and 2WikiQA.

  5. Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models

    cs.SE 2025-06 conditional novelty 4.0 of 10

    Reasoning depth in code LLMs should be managed as a controllable resource across synthetic data generation, benchmarking, and deployment, rather than left implicit.

Pith tools