Pith. sign in

REVIEW 3 cited by

Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.01796 v2 pith:RZANHGXR submitted 2024-07-01 cs.CL

Sirui Xia , Xintao Wang , Jiaqing Liang , Yifei Zhang , Weikang Zhou , Jiaji Deng , Fei Yu , Yanghua Xiao This is my paper
classification cs.CL
keywords generationcitationsreclaimcoarse-grainedenhanceextensivellmsprovides
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-Augmented Generation (RAG) has been widely adopted to enhance Large Language Models (LLMs) in knowledge-intensive tasks. To enhance credibility and verifiability in RAG systems, Attributed Text Generation (ATG) is proposed, which provides citations to retrieval knowledge in LLM-generated responses. Prior methods mainly adopt coarse-grained attributions, with passage-level or paragraph-level references or citations, which fall short in verifiability. This paper proposes ReClaim (Refer & Claim), a fine-grained ATG method that alternates the generation of references and answers step by step. Different from previous coarse-grained attribution, ReClaim provides sentence-level citations in long-form question-answering tasks. With extensive experiments, we verify the effectiveness of ReClaim in extensive settings, achieving a citation accuracy rate of 90%.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Lessons from Training Grounded LLMs with Verifiable Rewards

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A two-stage GRPO reward scheme improves citation-grounded answering and refusal in RAG models, with reasoning models benefiting more than instruction-tuned ones.

  2. The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems

    cs.IR 2025-05 conditional novelty 6.0 of 10

    A reinforcement-learning attack that swaps a few words in a single document pushes it into a black-box RAG system's top-3 results and flips the generated answer around 45-47% of the time.

  3. Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems

    cs.IR 2025-05 conditional novelty 5.0 of 10

    Wrapping erroneous knowledge in a reasoning model's own chain-of-thought template raises poisoning attack success on an R1-based RAG system by 10 percentage points over the strongest prior method in a 100-query MS MARCO test.

Pith tools