Markus Leippold, Mrinmaya Sachan, Elliott Ash, Jingwei Ni, Dominik Stammbach, Minjing Shi
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
With the rise of generative AI, automated factchecking methods to combat misinformation are becoming more and more important. However, factual claim detection, the first step in a fact-checking pipeline, suffers from two key issues that limit its scalability and generalizability: (1) inconsistency in definitions of the task and what a claim is, and (2) the high cost of manual annotation. To address (1), we review the definitions in related work and propose a unifying definition of factual claims that focuses on verifiability. To address (2), we introduce AFaCTA (Automatic Factual Claim deTection Annotator), a novel framework that assists in the annotation of factual claims with the help of large language models (LLMs). AFaCTA calibrates its annotation confidence with consistency along three predefined reasoning paths. Extensive evaluation and experiments in the domain of political speech reveal that AFaCTA can efficiently assist experts in annotating factual claims and training highquality classifiers, and can work with or without expert supervision. Our analyses also result in PoliClaim, a comprehensive claim detection dataset spanning diverse political topics. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2402.11073")
get_code_for_paper("2402.11073")
have("2402.11073")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2402.11073.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2402.11073)
Connect an agent — have() is free.