REVIEW 7 cited by
Fact-Checking Complex Claims with Program-Guided Reasoning
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
Fact-checking real-world claims often requires collecting multiple pieces of evidence and applying complex multi-step reasoning. In this paper, we present Program-Guided Fact-Checking (ProgramFC), a novel fact-checking model that decomposes complex claims into simpler sub-tasks that can be solved using a shared library of specialized functions. We first leverage the in-context learning ability of large language models to generate reasoning programs to guide the verification process. Afterward, we execute the program by delegating each sub-task to the corresponding sub-task handler. This process makes our model both explanatory and data-efficient, providing clear explanations of its reasoning process and requiring minimal training data. We evaluate ProgramFC on two challenging fact-checking datasets and show that it outperforms seven fact-checking baselines across different settings of evidence availability, with explicit output programs that benefit human debugging. Our codes and data are publicly available at https://github.com/mbzuai-nlp/ProgramFC.
Forward citations
Cited by 7 Pith papers
-
Personalized Large Language Models Can Increase the Belief Accuracy of Social Networks
A pre-registered experiment finds that adding a personalized, factually grounded LLM to an online discussion moves individuals' beliefs toward the truth and makes them build more accurate social networks.
-
Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection
A decoding pipeline reuses cached tokens and anneals sampling temperature to accelerate self-consistency hallucination detection by up to 3x without meaningful AUROC loss.
-
SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing
SUCEA improves adversarial fact-checking by decomposing claims into atomic sub-claims, editing each sub-claim toward retrieved evidence, and re-retrieving before predicting the final label.
-
Recon, Answer, Verify: Agents in Search of Truth
Removing annotator cues from fact-checking evidence lowers LLM scores substantially, and a three-agent question-answering pipeline, RAV, outperforms several published fact-checking baselines.
-
RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking
A new 6K-claim benchmark evaluates LLMs and multimodal LLMs on real-world fact-checking with an explicit 'unknown' option and shows web search and multimodal input improve performance.
-
LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification
LRCTI uses an LLM to summarize threat reports, retrieve evidence in several rounds, and judge each claim credible or incredible, reporting strong F1 gains on CTI-200 and PolitiFact.
-
AI-Generated Content in Cross-Domain Applications: Research Trends, Challenges and Propositions
A cross-domain vision paper that surveys AI-generated content and proposes research directions, without introducing new empirical results.
Discussion (0). Continue with ORCID to comment.