paper-with-me

홈 › Papers

Verifiable Generation with Subsentence-Level Fine-Grained Citations

2024-06-10 · Shuyang Cao, Lu Wang

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.

📄 PDF Abstract BibTeX arXiv:2406.06125

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceSpecificity

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation

2024-05-22 · Dimitris Gkoumas, Maria Liakata

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+1

ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification

2025-10-14 · Utsav Kumar Nareti, Suraj Kumar, Soumya Pandey, Soumi Chattopadhyay 외 arxiv

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 Classification

SSPO: Subsentence-level Policy Optimization

2025-11-06 · Kun Yang, Zikang chen, Yanmeng Wang, Zhigen Li 외 arxiv

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 Learning

Not Just Plain Text! Fuel Document-Level Relation Extraction with Explicit Syntax Refinement and Subsentence Modeling

2022-11-10 · Zhichao Duan, Xiuxing Li, Zhenyu Li, Zhuo Wang 외

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 Extraction

EgoCoT-Bench: Benchmarking Grounded and Verifiable Operation-Centric Chain of Thought Reasoning for MLLMs

2026-05-19 · Yang Dai, Dian Jiao, Tianwei Lin, Wenqiao Zhang arxiv

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…