paper-with-me

홈 › Papers

PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning

2025-07-25 · Mohammad Kachuee, Teja Gollapudi, Minseok Kim, Yin Huang, Kai Sun, Xiao Yang, Jiaqi Wang, Nirav Shah, Yue Liu, Aaron Colak, Anuj Kumar, Wen-tau Yih, Xin Luna Dong arxiv

Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual understanding and reasoning. We propose an efficient fine-tuning framework, called PrismRAG, that (i) trains the model with distractor-aware QA pairs mixing gold evidence with subtle distractor passages, and (ii) instills reasoning-centric habits that make the LLM plan, rationalize, and synthesize without relying on extensive human engineered instructions. Evaluated across 12 open-book RAG QA benchmarks spanning diverse application domains and scenarios, PrismRAG improves average factuality by 5.4%, outperforming state-of-the-art solutions.

📄 PDF Abstract BibTeX arXiv:2507.18857

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights

2026-03-17 · Yi Chen, Daiwei Chen, Sukrut Madhav Chikodikar, Caitlyn Heqi Yin 외 arxiv

Large language models (LLMs) frequently hallucinate, limiting their reliability in knowledge-intensive applications. Retrieval-augmented generation (RAG) and conformal factuality have emerged as potential ways to address…

Lost in the Noise: How Reasoning Models Fail with Contextual Distractors

2026-01-12 · Seongyun Lee, Yongrae Jo, Minju Seo, Moontae Lee 외 arxiv

Recent advances in reasoning models and agentic AI systems have led to an increased reliance on diverse external information. However, this shift introduces input contexts that are inherently noisy, a reality that curren…

REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy

2024-06-11 · Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna 외

Decoding methods for large language models (LLMs) usually struggle with the tradeoff between ensuring factuality and maintaining diversity. For example, a higher p threshold in the nucleus (top-p) sampling increases the …

DiversityHallucination

Few-Shot Object Detection via Classification Refinement and Distractor Retreatment

2021-06-19 · CVPR 2021 1 · Yiting Li, Haiyue Zhu, Yu Cheng, Wenxin Wang 외

We aim to tackle the challenging Few-Shot Object Detection (FSOD) where data-scarce categories are presented during the model learning. The failure modes of FSOD are investigated that the performance degradation is m…

ClassificationFew-Shot Object Detectionobject-detectionObject Detection

A Resilient Distributed Boosting Algorithm

2022-06-09 · Yuval Filmus, Idan Mehalel, Shay Moran

Given a learning task where the data is distributed among several parties, communication is one of the fundamental resources which the parties would like to minimize. We present a distributed boosting algorithm which is …

LEMMA