paper-with-me

홈 › Papers

Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models

2025-01-14 · Yifu Qiu, Varun Embar, Yizhe Zhang, Navdeep Jaitly, Shay B. Cohen, Benjamin Han

Recent advancements in long-context language models (LCLMs) promise to transform Retrieval-Augmented Generation (RAG) by simplifying pipelines. With their expanded context windows, LCLMs can process entire knowledge bases and perform retrieval and reasoning directly -- a capability we define as In-Context Retrieval and Reasoning (ICR^2). However, existing benchmarks like LOFT often overestimate LCLM performance by providing overly simplified contexts. To address this, we introduce ICR^2, a benchmark that evaluates LCLMs in more realistic scenarios by including confounding passages retrieved with strong retrievers. We then propose three methods to enhance LCLM performance: (1) retrieve-then-generate fine-tuning, (2) retrieval-attention-probing, which uses attention heads to filter and de-noise long contexts during decoding, and (3) joint retrieval head training alongside the generation head. Our evaluation of five well-known LCLMs on LOFT and ICR^2 demonstrates significant gains with our best approach applied to Mistral-7B: +17 and +15 points by Exact Match on LOFT, and +13 and +2 points on ICR^2, compared to vanilla RAG and supervised fine-tuning, respectively. It even outperforms GPT-4-Turbo on most tasks despite being a much smaller model.

📄 PDF Abstract BibTeX arXiv:2501.08248

Code (0)

등록된 구현이 없습니다.

Tasks

RAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
WordPiece 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations

2024-10-30 · Leonardo Ranaldi, Marco Valentino, Andrè Freitas

Retrieval-augmented generation (RAG) has emerged as a critical mechanism in contemporary NLP to support Large Language Models(LLMs) in systematically accessing richer factual context. However, the integration of RAG mech…

RAGRetrievalRetrieval-augmented Generation

RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval

2026-04-10 · Kyle Whitecross, Negin Rahimi arxiv

We propose RecaLLM, a set of reasoning language models post-trained to make effective use of long-context information. In-context retrieval, which identifies relevant evidence from context, and reasoning are deeply inter…

Semantic Retrieval

TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning

2026-02-15 · Nicolas Zumarraga, Thomas Kaar, Ning Wang, William Tennien 외 arxiv

Time Series Language Models (TSLMs) promise reasoning over real-world temporal data, but their ability to retrieve and reason over long time-series remains largely untested. We introduce TS-Haystack, a multi-domain retri…

Anomaly Detection

Rethinking Reasoning in LLMs: Neuro-Symbolic Local RetoMaton Beyond ICL and CoT

2025-08-22 · Rushitha Santhoshi Mamidala, Anshuman Chhabra, Ankur Mali arxiv

Prompt-based reasoning strategies such as Chain-of-Thought (CoT) and In-Context Learning (ICL) have become widely used for eliciting reasoning capabilities in large language models (LLMs). However, these methods rely on …

Reading Comprehension

HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning

2026-06-03 · Zeju Li, Ziyang Zheng, Yizhou Zhou, Qiang Xu arxiv

Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and accumulated interaction histories. Standard retrieval-augmented generation reduces this proble…