Pith. sign in

REVIEW 5 cited by

RbFT: Robust Fine-tuning for Retrieval-Augmented Generation against Retrieval Defects

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 2501.18365 v1 pith:42YVF27V submitted 2025-01-30 cs.CL cs.IR

Yiteng Tu , Weihang Su , Yujia Zhou , Yiqun Liu , Qingyao Ai This is my paper
classification cs.CLcs.IR
keywords retrievalfine-tuningknowledgerbftbasedefectsgenerationllms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamentally constrained by the reliability of both the retriever and the knowledge base. In real-world scenarios, imperfections in these components often lead to the retrieval of noisy, irrelevant, or misleading counterfactual information, ultimately undermining the trustworthiness of RAG systems. To address this challenge, we propose Robust Fine-Tuning (RbFT), a method designed to enhance the resilience of LLMs against retrieval defects through two targeted fine-tuning tasks. Experimental results demonstrate that RbFT significantly improves the robustness of RAG systems across diverse retrieval conditions, surpassing existing methods while maintaining high inference efficiency and compatibility with other robustness techniques.

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. Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees

    cs.LG 2026-07 conditional novelty 6.0 of 10

    C3R certifies per-domain retrieval contamination budgets using a two-split conformal scheme, without query-time domain labels.

  2. 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.

  3. Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing

    cs.CL 2025-05 conditional novelty 6.0 of 10

    DecKER decouples reasoning from knowledge editing by planning with masked placeholders before retrieving edited facts, improving multi-hop QA accuracy after knowledge edits.

  4. Curriculum Guided Reinforcement Learning for Efficient Multi Hop Retrieval Augmented Generation

    cs.CL 2025-05 reject novelty 5.0 of 10

    EVO-RAG applies curriculum-guided reinforcement learning with time-varying reward weights to multi-hop RAG, reporting improved EM on HotpotQA, 2WikiMultiHopQA, and MuSiQue.

  5. Dynamic and Parametric Retrieval-Augmented Generation

    cs.CL 2025-06 unverdicted novelty 2.0 of 10

    A tutorial outline that categorizes recent RAG work into Dynamic RAG and Parametric RAG, and explains why both are needed.

Pith tools