Verifiable Generation with Subsentence-Level Fine-Grained Citations
Verifiable generation requires large language models (LLMs) to cite source documents supporting their outputs, thereby improve output transparency and trustworthiness. Yet, previous work mainly targets the generation of sentence-level citations, lacking specificity about which parts of a sentence are backed by the cited sources. This work studies verifiable generation with subsentence-level fine-grained citations for more precise location of generated content supported by the cited sources. We first present a dataset, SCiFi, comprising 10K Wikipedia paragraphs with subsentence-level citations. Each paragraph is paired with a set of candidate source documents for citation and a query that triggers the generation of the paragraph content. On SCiFi, we evaluate the performance of state-of-the-art LLMs and strategies for processing long documents designed for these models. Our experiment results reveals key factors that could enhance the quality of citations, including the expansion of the source documents' context accessible to the models and the implementation of specialized model tuning.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceSpecificityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation
Scientific language models drive research innovation but require extensive fine-tuning on large datasets. This work enhances such models by improving their inference and evaluation capabilities with minimal or no additio…
Caption GenerationHallucinationNatural Language Inferencescientific discovery+1ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification
The rapid growth of user-generated text across digital platforms has intensified the need for interpretable models capable of fine-grained text classification and explanation. Existing prototype-based models offer intuit…
Multi-Label Text ClassificationSSPO: Subsentence-level Policy Optimization
As a key component of large language model (LLM) post-training, Reinforcement Learning from Verifiable Rewards (RLVR) has substantially improved reasoning performance. However, existing RLVR algorithms exhibit distinct s…
Reinforcement LearningNot Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence Modeling
Document-level relation extraction (DocRE) aims to identify semantic labels among entities within a single document. One major challenge of DocRE is to dig decisive details regarding a specific entity pair from long text…
Document-level Relation ExtractionRelationRelation ExtractionEgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs
The rapid development of Multimodal Large Language Models (MLLMs) has led to growing interest in egocentric video understanding, specifically the ability for MLLMs to recognize fine-grained hand-object interactions, trac…