Pith. sign in

REVIEW 9 cited by

Rethinking with Retrieval: Faithful Large Language Model Inference

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 2301.00303 v1 pith:JCORMHNJ submitted 2022-12-31 cs.CL cs.AI

Rethinking with Retrieval: Faithful Large Language Model Inference

classification cs.CL cs.AI
keywords llmsreasoningknowledgeexternallanguageadditionalapproachfaithful
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize external knowledge to assist LLMs. Unfortunately, current methods for incorporating external knowledge often require additional training or fine-tuning, which can be costly and may not be feasible for LLMs. To address this issue, we propose a novel post-processing approach, rethinking with retrieval (RR), which retrieves relevant external knowledge based on the decomposed reasoning steps obtained from the chain-of-thought (CoT) prompting. This lightweight approach does not require additional training or fine-tuning and is not limited by the input length of LLMs. We evaluate the effectiveness of RR through extensive experiments with GPT-3 on three complex reasoning tasks: commonsense reasoning, temporal reasoning, and tabular reasoning. Our results show that RR can produce more faithful explanations and improve the performance of LLMs.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

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

  1. Diversity in Large Language Models under Supervised Fine-Tuning

    cs.LG 2026-04 unverdicted novelty 6.0

    TOFU loss mitigates the narrowing of generative diversity in LLMs after supervised fine-tuning by addressing neglect of low-frequency patterns and forgetting of prior knowledge.

  2. R$^3$AG: Retriever Routing for Retrieval-Augmented Generation

    cs.IR 2026-04 unverdicted novelty 6.0

    R³AG routes queries to retrievers by decomposing capabilities into retrieval quality and generation utility, trained via contrastive learning on document assessments and downstream answer correctness to outperform sta...

  3. Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models

    cs.AI 2025-06 conditional novelty 6.0

    Active Indexing with synthetic data augmentation for bidirectional fact-source binding during pretraining yields up to 30.2% higher citation precision than passive identifier appending on CitePretrainBench for Qwen models.

  4. NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning

    cs.CL 2026-06 unverdicted novelty 5.0

    NTS-CoT applies Element-CoT, Date Selection, and Causal-CoT modules to cut unfaithful content and omissions in LLM-based timeline summarization, outperforming baselines on three benchmarks.

  5. Diversity in Large Language Models under Supervised Fine-Tuning

    cs.LG 2026-04 unverdicted novelty 5.0

    Supervised fine-tuning narrows LLM generative diversity through neglect of low-frequency patterns and knowledge forgetting, but the TOFU loss mitigates this effect across models and benchmarks.

  6. VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection

    cs.CV 2026-04 unverdicted novelty 5.0

    VRAG-DFD uses RAG to retrieve forgery knowledge and RL-based training to build critical reasoning in MLLMs, delivering state-of-the-art generalization on deepfake detection tasks.

  7. Injecting Structured Biomedical Knowledge into Language Models: Continual Pretraining vs. GraphRAG

    cs.CL 2026-04 unverdicted novelty 5.0

    Continual pretraining on UMLS-derived text improves BERT on BLURB biomedical tasks while GraphRAG boosts LLaMA 3-8B accuracy by over 3 points on PubMedQA and 5 on BioASQ without retraining.

  8. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

    cs.CL 2023-11 unverdicted novelty 5.0

    The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.

  9. Deploying AI for Signal Processing education: Selected challenges and intriguing opportunities

    eess.SP 2025-09 conditional novelty 4.0

    AI can be used to generate interactive signal processing courseware, but the paper offers no evidence that students learn better from it.