Image de couverture de livre

Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lahmy, Moshe, Yozevitch, Roi
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test
par: Sartori, Camilo Chacón, et autres
Publié: (2026)

Don't Pay Attention
par: Hammoud, Mohammad, et autres
Publié: (2025)

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
par: Zhuang, Ziyuan, et autres
Publié: (2024)

Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing
par: Yang, Diji, et autres
Publié: (2025)

Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG
par: Chen, Xinxi, et autres
Publié: (2024)

Credible Plan-Driven RAG Method for Multi-Hop Question Answering
par: Zhang, Ningning, et autres
Publié: (2025)

Don't Forget to Connect! Improving RAG with Graph-based Reranking
par: Dong, Jialin, et autres
Publié: (2024)

Can LLMs Replace Economic Choice Prediction Labs? The Case of Language-based Persuasion Games
par: Shapira, Eilam, et autres
Publié: (2024)

Reasoning Models Reason Well, Until They Don't
par: Rameshkumar, Revanth, et autres
Publié: (2025)

Align, Don't Divide: Revisiting the LoRA Architecture in Multi-Task Learning
par: Liu, Jinda, et autres
Publié: (2025)

Multi-Meta-RAG: Improving RAG for Multi-Hop Queries using Database Filtering with LLM-Extracted Metadata
par: Poliakov, Mykhailo, et autres
Publié: (2024)

Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning
par: Qin, Yuehan, et autres
Publié: (2025)

What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA
par: Chang, Zhiyuan, et autres
Publié: (2024)

Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs
par: Thompson, Travis, et autres
Publié: (2025)

CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question Answering
par: Yang, Hao, et autres
Publié: (2026)

Language Models Don't Learn the Physical Manifestation of Language
par: Lee, Bruce W., et autres
Publié: (2024)

Can AI Assistants Know What They Don't Know?
par: Cheng, Qinyuan, et autres
Publié: (2024)

Don't Take Things Out of Context: Attention Intervention for Enhancing Chain-of-Thought Reasoning in Large Language Models
par: Yan, Shaotian, et autres
Publié: (2025)

Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
par: Sun, Yiqun, et autres
Publié: (2026)

The Poisoned Apple Effect: Strategic Manipulation of Mediated Markets via Technology Expansion of AI Agents
par: Shapira, Eilam, et autres
Publié: (2026)

Don't Lag, RAG: Training-Free Adversarial Detection Using RAG
par: Kazoom, Roie, et autres
Publié: (2025)

AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAG
par: Peng, Chao, et autres
Publié: (2025)

Don't Think Twice! Over-Reasoning Impairs Confidence Calibration
par: Lacombe, Romain, et autres
Publié: (2025)

sDPO: Don't Use Your Data All at Once
par: Kim, Dahyun, et autres
Publié: (2024)

Enhancing Neural Spoken Language Recognition: An Exploration with Multilingual Datasets
par: Anidjar, Or Haim, et autres
Publié: (2025)

s3: You Don't Need That Much Data to Train a Search Agent via RL
par: Jiang, Pengcheng, et autres
Publié: (2025)

Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
par: Kim, Woojin, et autres
Publié: (2025)

Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration
par: Mao, Xin, et autres
Publié: (2024)

Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding
par: Zhang, Kexun, et autres
Publié: (2023)

Do Retrieval Augmented Language Models Know When They Don't Know?
par: Zhou, Youchao, et autres
Publié: (2025)

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
par: Hassid, Michael, et autres
Publié: (2025)

Don't Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models
par: Bavaresco, A., et autres
Publié: (2024)

The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs
par: Calderon, Nitay, et autres
Publié: (2025)

Don't Change My View: Ideological Bias Auditing in Large Language Models
par: Kröger, Paul, et autres
Publié: (2025)

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
par: Mei, Zhiting, et autres
Publié: (2025)

Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning
par: He, Yongquan, et autres
Publié: (2024)

Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling
par: Shapira, Eilam, et autres
Publié: (2026)

Don't Just Demo, Teach Me the Principles: A Principle-Based Multi-Agent Prompting Strategy for Text Classification
par: Wei, Peipei, et autres
Publié: (2025)

Reasoning Models Don't Always Say What They Think
par: Chen, Yanda, et autres
Publié: (2025)

Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMs
par: Singhal, Ronit, et autres
Publié: (2024)