REVIEW 7 cited by
Boosting Language Models Reasoning with Chain-of-Knowledge Prompting
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
Recently, Chain-of-Thought (CoT) prompting has delivered success on complex reasoning tasks, which aims at designing a simple prompt like ``Let's think step by step'' or multiple in-context exemplars with well-designed rationales to elicit Large Language Models (LLMs) to generate intermediate reasoning steps. However, the generated rationales often come with mistakes, making unfactual and unfaithful reasoning chains. To mitigate this brittleness, we propose a novel Chain-of-Knowledge (CoK) prompting, where we aim at eliciting LLMs to generate explicit pieces of knowledge evidence in the form of structure triple. This is inspired by our human behaviors, i.e., we can draw a mind map or knowledge map as the reasoning evidence in the brain before answering a complex question. Benefiting from CoK, we additionally introduce a F^2-Verification method to estimate the reliability of the reasoning chains in terms of factuality and faithfulness. For the unreliable response, the wrong evidence can be indicated to prompt the LLM to rethink. Extensive experiments demonstrate that our method can further improve the performance of commonsense, factual, symbolic, and arithmetic reasoning tasks.
Forward citations
Cited by 7 Pith papers
-
AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation
AutoLaw's verifier-ranked legal-role jury with a similar-case demonstration beats majority voting for violation detection on three law and policy benchmarks.
-
CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning
CDW-CoT groups a reasoning dataset into clusters, learns a prompt distribution per cluster, and interpolates these distributions by embedding distance for each new query, reporting higher exact-match accuracy than thr...
-
GRL-Prompt: Towards Knowledge Graph based Prompt Optimization via Reinforcement Learning
A knowledge-graph-based reinforcement learning policy selects and orders in-context examples for LLM prompts, reporting modest ROUGE and BLEU improvements.
-
GraPPI: A Retrieve-Divide-Solve GraphRAG Framework for Large-scale Protein-protein Interaction Exploration
A knowledge-graph-based RAG framework that splits PPI pathway exploration into edge-level subtasks and returns ranked, explained pathways from the STRING interaction database.
-
ADKGD: Anomaly Detection in Knowledge Graphs with Dual-Channel Training
A dual-channel training method with KL consistency loss is proposed for knowledge graph anomaly detection, but reported state-of-the-art claims are contradicted by the paper's own comparisons.
-
Enhancing the Reasoning Capabilities of Small Language Models via Solution Guidance Fine-Tuning
SGFT fine-tunes a small model to produce calculation-free solution plans and uses a second model to answer from them, outperforming CoT fine-tuning with roughly 3% of the training data.
-
Enhancing Large Language Models with Reliable Knowledge Graphs
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.
Discussion (0). Continue with ORCID to comment.