REVIEW 20 cited by
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
Not yet reviewed by Pith; the record is open.
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
LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs
read the original abstract
In traditional RAG framework, the basic retrieval units are normally short. The common retrievers like DPR normally work with 100-word Wikipedia paragraphs. Such a design forces the retriever to search over a large corpus to find the `needle' unit. In contrast, the readers only need to generate answers from the short retrieved units. The imbalanced `heavy' retriever and `light' reader design can lead to sub-optimal performance. The loss of contextual information in the short, chunked units may increase the likelihood of introducing hard negatives during the retrieval stage. Additionally, the reader might not fully leverage the capabilities of recent advancements in LLMs. In order to alleviate the imbalance, we propose a new framework LongRAG, consisting of a `long retriever' and a `long reader'. In the two Wikipedia-based datasets, NQ and HotpotQA, LongRAG processes the entire Wikipedia corpus into 4K-token units by grouping related documents. By increasing the unit size, we significantly reduce the total number of units. This greatly reduces the burden on the retriever, resulting in strong retrieval performance with only a few (less than 8) top units. Without requiring any training, LongRAG achieves an EM of 62.7% on NQ and 64.3% on HotpotQA, which are on par with the (fully-trained) SoTA model. Furthermore, we test on two non-Wikipedia-based datasets, Qasper and MultiFieldQA-en. LongRAG processes each individual document as a single (long) unit rather than chunking them into smaller units. By doing so, we achieve an F1 score of 25.9% on Qasper and 57.5% on MultiFieldQA-en. Our study offers insights into the future roadmap for combining RAG with long-context LLMs.
Forward citations
Cited by 20 Pith papers
-
Evidence-State Rewards for Long-Context Reasoning
Maven is an RL method using answer-conditioned evidence-state values to assign rewards to add, link, and drop actions on evidence memory, outperforming outcome-only baselines on LongBench v2, LongReason, and RULER.
-
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
MemLens benchmark shows long-context LVLMs lose accuracy with length while memory agents lose visual fidelity, with multi-session reasoning below 30% for most systems and neither approach solving the task alone.
-
IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review
IntrAgent uses a two-stage pipeline of section ranking and iterative reading to perform content-grounded literature information retrieval, achieving 13.2% higher accuracy than RAG and agent baselines on the new IntraB...
-
SimpleWikiSearch: A Clean Offline Wikipedia Environment for Agentic Search
SimpleWikiSearch provides an explicit, runnable offline Wikipedia testbed—corpus, retrieval, and a three-tool agent contract—that makes LLM agentic-search evaluation reproducible and comparable.
-
Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
UMG-RAG improves long-document RAG by uncertainty-aware fusion of multi-granularity retrievals from complementary dense and sparse retrievers, plus a parent-promotion variant.
-
HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning
HMARS introduces a hierarchical multi-agent memory system that outperforms standard retrieval and other baselines on long-document and multi-turn reasoning tasks through improved evidence coverage.
-
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
-
An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration
Experience-RAG Skill uses experience memory to dynamically select retrieval strategies for agents, achieving 0.8924 nDCG@10 on BeIR/nq, hotpotqa, and scifact while outperforming fixed single-retriever baselines.
-
SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing
SAGE is a training-free context reduction method that converts attention signals from a small LLM into a differential relevance heatmap to select top units for downstream QA, achieving competitive accuracy at 10% toke...
-
Beyond RAG for Cyber Threat Intelligence: A Systematic Evaluation of Graph-Based and Agentic Retrieval
A hybrid graph-text retrieval system for cyber threat intelligence improves multi-hop question answering by up to 35% over vector-based RAG on a 3,300-question benchmark.
-
DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking
DualView fuses local cross-attention and global context aggregation via adaptive gating to rerank fixed candidate sets for multi-hop QA, reporting 99.4% Top-4 Recall on MuSiQue at 4 ms latency while beating larger cro...
-
Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking
UPipe chunks attention by head so QKV and all-to-all buffers scale with a small tunable chunk size rather than head count, enabling 5M-token Llama3-8B training on one 8×H100 node with throughput close to Ulysses.
-
Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering
A condition-gated knowledge-graph method improves biomedical QA when patient-specific contraindications change the correct answer, and a new 100-question benchmark measures this capability.
-
Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation
EviOmni unifies evidence reasoning and extraction in a single RL trajectory with token masking and verifiable rewards for answer, length, and format to produce compact high-quality evidence for RAG.
-
Supervising the search process produces reliable and generalizable information-seeking agents
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
-
Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation
Enforcing sentence-level citations degrades LLM attribution quality by 16-276% versus paragraph-level, with larger models penalized more due to disrupted semantic synthesis.
-
Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off
Hybrid Document-Routed Retrieval (HDRR) filters financial filings with LLM document routing then scopes chunk retrieval, beating pure chunk and pure file routing on FinDER accuracy and efficiency.
-
Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off
HDRR combines document-level semantic routing with scoped chunk retrieval to outperform both pure chunk-based retrieval and semantic file routing on the FinDER benchmark, delivering higher average scores, lower failur...
-
An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration
Experience-RAG Skill is a reusable agent skill that selects retrieval strategies via experience memory, achieving 0.8924 nDCG@10 on BeIR/nq, hotpotqa, and scifact while outperforming fixed retriever baselines.
-
A Survey of Scaling in Large Language Model Reasoning
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.