Fine-tuned Mistral-7B via QLoRA achieves up to 12% higher F1 than GPT-4o on biomedical claim verification with 1008 examples, identifies a structural shortcut in SciFact, and shows robust cross-domain transfer from sound data.
Explainable automated fact-checking for public health claims
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 3roles
dataset 1polarities
use dataset 1representative citing papers
By steering activations along directions learned from base-vs-fine-tuned disagreements, REFLEX reports 64.99 macro-F1 on RAW-FC fact-checking with only ~465 self-refined contrastive samples and no retrieval.
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
citing papers explorer
-
Small LLMs for Biomedical Claim Verification: Cost-Effective Fine-Tuning, Structural Dataset Shortcuts, and Cross-Domain Generalization
Fine-tuned Mistral-7B via QLoRA achieves up to 12% higher F1 than GPT-4o on biomedical claim verification with 1008 examples, identifies a structural shortcut in SciFact, and shows robust cross-domain transfer from sound data.
-
REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control
By steering activations along directions learned from base-vs-fine-tuned disagreements, REFLEX reports 64.99 macro-F1 on RAW-FC fact-checking with only ~465 self-refined contrastive samples and no retrieval.
-
Retrieval-Augmented Generation for Large Language Models: A Survey
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.