Explicit Evidence Grounding via Structured Inline Citation Generation
As AI systems become more widely adopted, the demand for factual and faithful generation grows. Properly attributing information through citations becomes, therefore, crucial. This work introduces FullCite, a framework that, in contrast to most previous works, generates structured inline citations linking each claim to both its source document and supporting evidence. FullCite proposes three strategies to inline citation generation: prompt-based generation, constrained decoding over a citation grammar, and posthoc span alignment. Using three question answering benchmarks, namely, ASQA, BioASQ, and ExpertQA, we assess citation quality and faithfulness along three dimensions: document-level correctness, evidence span identification, and claim-citation faithfulness. Our evaluation shows that while LLMs are generally effective at identifying relevant documents, they struggle to identify the precise supporting spans within them. This gap suggests that achieving faithful attributed QA will require research to place greater emphasis on precise evidence span identification.
Code (0)
등록된 구현이 없습니다.
Tasks
Question AnsweringSimilar Papers 제목 키워드 기반
CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering
Long-form question answering increasingly relies on retrieved evidence to make LLM outputs verifiable, with inline citations tracing claims to source documents. However, existing systems often attach citations that are t…
Question AnsweringAnswer GenerationHow Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) aims to enhance the trustworthiness of Large Language Models (LLMs) by grounding their outputs in external documents, often using inline citations for verifiability. However, the fait…
CaVe-VLM-CoT: An Interpretable Vision-Language Model Framework
Vision-Language Models (VLMs) remain prone to hallucinations, producing fluent but visually unfaithful outputs. Existing chain-of-thought and retrieval-augmented methods only partially address this, as they neither enfor…
The Provenance Gap in Clinical AI: Evidence-Traceable Temporal Knowledge Graphs for Rare Disease Reasoning
Frontier large language models generate clinically accurate outputs, but their citations are often fabricated. We term this the Provenance Gap. We tested five frontier LLMs across 36 clinician-validated scenarios for thr…
Knowledge GraphsTRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation
Multi-video event understanding demands models that can locate and attribute query-relevant evidence scattered across long, heterogeneous video corpora. Existing large vision-language models (LVLMs) often underperform in…
Object DetectionVisual Reasoning