Pith. sign in

REVIEW 5 cited by

ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems

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 2410.19572 v5 pith:7OLREGPT submitted 2024-10-25 cs.CL

Ishneet Sukhvinder Singh , Ritvik Aggarwal , Ibrahim Allahverdiyev , Muhammad Taha , Aslihan Akalin , Kevin Zhu , Sean O'Brien This is my paper
classification cs.CL
keywords filteringsystemschunkinformationaccuracychunkragenhancesexisting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-Augmented Generation (RAG) systems using large language models (LLMs) often generate inaccurate responses due to the retrieval of irrelevant or loosely related information. Existing methods, which operate at the document level, fail to effectively filter out such content. We propose LLM-driven chunk filtering, ChunkRAG, a framework that enhances RAG systems by evaluating and filtering retrieved information at the chunk level. Our approach employs semantic chunking to divide documents into coherent sections and utilizes LLM-based relevance scoring to assess each chunk's alignment with the user's query. By filtering out less pertinent chunks before the generation phase, we significantly reduce hallucinations and improve factual accuracy. Experiments show that our method outperforms existing RAG models, achieving higher accuracy on tasks requiring precise information retrieval. This advancement enhances the reliability of RAG systems, making them particularly beneficial for applications like fact-checking and multi-hop reasoning.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Agents-K1: Towards Agent-native Knowledge Orchestration

    cs.AI 2026-06 unverdicted novelty 6.0 of 10

    Agents-K1 is an end-to-end pipeline with a multimodal parser, 4B GRPO-trained extractor, and agent CLI that builds scientific knowledge graphs from full papers and was run on 2.46 million documents to produce Scholar-KG.

  2. PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs

    cs.AI 2026-07 conditional novelty 5.0 of 10

    A structure-aware web RAG system over a three-layer heterogeneous graph routes queries to block, navigation, or entity modes and outperforms prior RAG baselines on PolyU website QA with lower token cost.

  3. System Prompt Extraction Attacks and Defenses in Large Language Models

    cs.CR 2025-05 conditional novelty 4.0 of 10

    A benchmarking study shows that chain-of-thought, few-shot, and modified sandwich queries can recover LLM system prompts with high similarity-based success, and output filtering is the most reliable tested defense.

  4. Two-way Evidence self-Alignment based Dual-Gated Reasoning Enhancement

    cs.CL 2025-05 conditional novelty 4.0 of 10

    ESA-DGR combines two-way evidence self-alignment with dual-gated knowledge fusion and GRPO training to improve multi-hop question answering on HotpotQA, 2WikiMultiHopQA, and MuSiQue.

  5. The Effect of Text Chunk Size on Retrieval-Augmented Generation Performance

    cs.IR 2026-06 reject novelty 3.0 of 10

    The paper reports paragraph chunks best for a math textbook and sentence chunks best for a narrative, but its conclusion says the opposite for narrative and never measures generation quality.

Pith tools