Pith. sign in

REVIEW 9 cited by

Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2308.13259 v2 pith:6FE7OF32 submitted 2023-08-25 cs.CL cs.AI

Keheng Wang , Feiyu Duan , Sirui Wang , Peiguang Li , Yunsen Xian , Chuantao Yin , Wenge Rong , Zhang Xiong This is my paper · ORCID
classification cs.CLcs.AI
keywords reasoningllmsknowledgeexternalkd-cotansweringchain-of-thoughtfaithful
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Equipped with Chain-of-Thought (CoT), Large language models (LLMs) have shown impressive reasoning ability in various downstream tasks. Even so, suffering from hallucinations and the inability to access external knowledge, LLMs often come with incorrect or unfaithful intermediate reasoning steps, especially in the context of answering knowledge-intensive tasks such as KBQA. To alleviate this issue, we propose a framework called Knowledge-Driven Chain-of-Thought (KD-CoT) to verify and modify reasoning traces in CoT via interaction with external knowledge, and thus overcome the hallucinations and error propagation. Concretely, we formulate the CoT rationale process of LLMs into a structured multi-round QA format. In each round, LLMs interact with a QA system that retrieves external knowledge and produce faithful reasoning traces based on retrieved precise answers. The structured CoT reasoning of LLMs is facilitated by our developed KBQA CoT collection, which serves as in-context learning demonstrations and can also be utilized as feedback augmentation to train a robust retriever. Extensive experiments on WebQSP and ComplexWebQuestion datasets demonstrate the effectiveness of proposed KD-CoT in task-solving reasoning generation, which outperforms the vanilla CoT ICL with an absolute success rate of 8.0% and 5.1%. Furthermore, our proposed feedback-augmented retriever outperforms the state-of-the-art baselines for retrieving knowledge, achieving significant improvement in Hit and recall performance. Our code and data are released on https://github.com/AdelWang/KD-CoT/tree/main.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

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

  1. Logic-Guided Socially-aware Robot Navigation World Model

    cs.RO 2025-10 conditional novelty 6.0 of 10

    NaviWM couples a spatial-temporal world model with a deductive chain-of-thought, formalizing social navigation rules as first-order logic, and reports improved success and lower violation rates in simulated crowded na...

  2. BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering

    cs.CL 2025-07 reject novelty 6.0 of 10

    BYOKG-RAG combines LLM-generated entities, paths, queries, and candidate answers with multiple graph retrieval tools to answer questions over custom knowledge graphs without training data.

  3. Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    ReG refines weak graph-retriever supervision with LLM-selected reasoning chains and reorganizes retrieved triples into coherent evidence chains, improving KGQA accuracy, data efficiency, and reasoning token efficiency.

  4. Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering

    cs.CL 2025-06 conditional novelty 6.0 of 10

    RAPL combines LLM-rationalized path labels, line graph transformation, and path-based decoding to improve graph retrieval for KGQA, reporting state-of-the-art results on WebQSP and CWQ.

  5. RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation

    cs.CL 2026-07 conditional novelty 5.0 of 10

    RSF-GLLM decouples differentiable graph reasoning (via a GRU-guided soft-flow module with dynamic gating) from LLM generation to efficiently bridge semantic gaps in multi-hop KGQA.

  6. Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs

    cs.CL 2025-06 conditional novelty 5.0 of 10

    RRP generates semantic and structural reasoning paths, reranks them with a rethinking module, and reports SOTA Hits@1 of 90.0 on WebQSP and 64.5 on CWQ.

  7. Paths to Causality: Finding Informative Subgraphs Within Knowledge Graphs for Knowledge-Based Causal Discovery

    cs.AI 2025-06 conditional novelty 5.0 of 10

    A learning-to-rank model chooses informative knowledge-graph paths between entity pairs, and adding the top path to zero-shot prompts improves LLM causal classification by up to 44.4 F1 points.

  8. HaluNet: Learning Hallucination Risk from Internal Signals in LLM Question Answering

    cs.CL 2025-12 conditional novelty 4.0 of 10

    HaluNet fuses token-level log-likelihood, entropy, and hidden-state embeddings via a multi-branch neural network to rank hallucinated LLM QA answers with reported AUROC up to 0.922 in-domain.

  9. Enhancing Large Language Models with Reliable Knowledge Graphs

    cs.CL 2025-06 conditional novelty 2.0 of 10

    A thesis composed of four published papers proposes contrastive KG error detection, attribute-aware error-aware embedding, inductive graph completion, and KG prompting, but adds no new result beyond those papers.

Pith tools