Pith. sign in

REVIEW 9 cited by

Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG

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 2410.05983 v1 pith:5P6F4JQ7 submitted 2024-10-08 cs.CL cs.AIcs.LG

Bowen Jin , Jinsung Yoon , Jiawei Han , Sercan O. Arik This is my paper
classification cs.CLcs.AIcs.LG
keywords llmslong-contextretrievedtraining-basedcapacityenhancefine-tuningfirst
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-augmented generation (RAG) empowers large language models (LLMs) to utilize external knowledge sources. The increasing capacity of LLMs to process longer input sequences opens up avenues for providing more retrieved information, to potentially enhance the quality of generated outputs. It is plausible to assume that a larger retrieval set would contain more relevant information (higher recall), that might result in improved performance. However, our empirical findings demonstrate that for many long-context LLMs, the quality of generated output initially improves first, but then subsequently declines as the number of retrieved passages increases. This paper investigates this phenomenon, identifying the detrimental impact of retrieved "hard negatives" as a key contributor. To mitigate this and enhance the robustness of long-context LLM-based RAG, we propose both training-free and training-based approaches. We first showcase the effectiveness of retrieval reordering as a simple yet powerful training-free optimization. Furthermore, we explore training-based methods, specifically RAG-specific implicit LLM fine-tuning and RAG-oriented fine-tuning with intermediate reasoning, demonstrating their capacity for substantial performance gains. Finally, we conduct a systematic analysis of design choices for these training-based methods, including data distribution, retriever selection, and training context length.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

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

  1. Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks

    cs.CL 2025-07 conditional novelty 7.0 of 10

    A compact, diverse, web-scale datastore plus simple dense retrieval improves performance on MMLU, MMLU Pro, AGI Eval, GPQA, and MATH across multiple LLM families.

  2. Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG

    cs.CL 2025-09 conditional novelty 6.0 of 10

    In multilingual retrieval-augmented generation, models cite English evidence more accurately than translated evidence, and this language preference can outweigh document relevance.

  3. Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    ReG refines weak graph-retriever supervision with LLM-selected reasoning chains and reorganizes retrieved triples into coherent evidence chains, improving KGQA accuracy, data efficiency, and reasoning token efficiency.

  4. Maximally-Informative Retrieval for State Space Model Generation

    cs.CL 2025-06 conditional novelty 6.0 of 10

    RICO ranks documents by how much they reduce an SSM's question perplexity, using gradient-document inner products, and matches BM25 while often beating E5 on answer quality without finetuning.

  5. Magic Mushroom: A Customizable Benchmark for Fine-grained Analysis of Retrieval Noise Erosion in RAG Systems

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A configurable benchmark with four retrieval-noise types shows RAG accuracy drops sharply beyond 50% noise and that noise type, not just quantity, determines failure patterns.

  6. Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    A new RL framework that rewards fine-grained reasoning steps, called Atomic Thoughts, claims better agentic deep research on seven benchmarks.

  7. Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering

    cs.CL 2025-07 conditional novelty 5.0 of 10

    AdaPCR jointly retrieves and reranks passage pairs for open-domain QA, showing small EM/F1 gains over an in-context retrieval baseline, mostly on multi-hop HotpotQA.

  8. VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

    cs.CL 2025-05 conditional novelty 5.0 of 10

    VRAG-RL uses GRPO reinforcement learning with visual cropping actions and a retrieval-aware reward to improve vision-language RAG agents on document benchmarks.

  9. Hierarchical Reranking for Scalable Financial RAG System

    cs.IR 2026-07 reject novelty 4.0 of 10

    A finance-specific RAG pipeline combining table-to-JSON conversion, two-stage reranking, and long-context split-fusion reports NDCG@20=0.7918 and second place in the ICAIF '24 FinanceRAG challenge.

Pith tools