No article text was recorded for this version.
relevance-utility gap
Version 1 of 1129 papers150 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Enhancing Large Language Models with Domain-specific Retrieval Augment Generation: A Case Study on Long-form Consumer Health Question Answering in Ophthalmology
- Blog: GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis
- Blog: Rethinking Relevance: How Noise and Distractors Impact Retrieval-Augmented Generation
- Blog: Calibrated Decision-Making through LLM-Assisted Retrieval
- Blog: RRAML: Reinforced Retrieval Augmented Machine Learning
- Blog: Evidentiality-aware Retrieval for Overcoming Abstractiveness in Open-Domain Question Answering
- Blog: OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning
- Blog: InfoGain-RAG: Boosting Retrieval-Augmented Generation via Document Information Gain-based Reranking and Filtering
- Blog: GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis
- Blog: Enhancing Generative Retrieval with Reinforcement Learning from Relevance Feedback
- Blog: W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering
- Blog: Optimizing Retrieval for RAG via Reinforcement Learning
- Blog: Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
- Blog: Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
- Blog: Preference-Guided Refactored Tuning for Retrieval Augmented Code Generation
- Blog: EAReranker: Efficient Embedding Adequacy Assessment for Retrieval Augmented Generation
- Blog: Aligning Retrieval with Reader Needs: Reader-Centered Passage Selection for Open-Domain Question Answering
- Blog: Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models
- Blog: Inference Scaling for Bridging Retrieval and Augmented Generation
- Blog: Leveraging Memory Retrieval to Enhance LLM-based Generative Recommendation
- Blog: Answering questions by learning to rank - Learning to rank by answering questions
- Blog: BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicine
- Blog: Learning deep structured semantic models for web search using clickthrough data
- Blog: ARL2: Aligning Retrievers with Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
- Blog: RetGen: A Joint Framework for Retrieval and Grounded Text Generation Modeling
- Blog: M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions
- Blog: A Multi-Task Embedder For Retrieval Augmented LLMs
- Blog: Rethinking LLM Parametric Knowledge as Post-retrieval Confidence for Dynamic Retrieval and Reranking
- Blog: Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models
- Blog: Reliable Decision‑Making via Calibration‑Oriented Retrieval‑Augmented Generation
- Blog: Aligning Large Language Models with Human Opinions through Persona Selection and Value-Belief-Norm Reasoning
- Blog: HYDRA: Model Factorization Framework for Black-Box LLM Personalization
- Blog: Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
- Blog: Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation
- Blog: GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking
- Blog: IRSum: One Model to Rule Summarization and Retrieval
- Blog: Unified Demonstration Retriever for In-Context Learning
- Blog: Bridging the Preference Gap between Retrievers and LLMs
- Blog: Lightweight and Direct Document Relevance Optimization for Generative Information Retrieval
- Blog: CiteME: Can Language Models Accurately Cite Scientific Claims?
- Blog: Joint Retrieval and Generation Training for Grounded Text Generation
- Blog: Contradiction Retrieval via Contrastive Learning with Sparsity
- Blog: RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert Collaboration
- Blog: RA-DIT: Retrieval-Augmented Dual Instruction Tuning
- Blog: Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In
- Blog: Evaluating Retrieval Quality in Retrieval-Augmented Generation
- Blog: Retrieving Comparative Arguments using Deep Pre-trained Language Models and NLU
- Blog: Learning Neural Representation for CLIR with Adversarial Framework
- Blog: Reliable, Adaptable, and Attributable Language Models with Retrieval
- Blog: All That Glitters is Not Gold: Improving Robust Retrieval-Augmented Language Models with Fact-Centric Preference Alignment
- Blog: Learning to Relate to Previous Turns in Conversational Search
- Blog: FineFilter: A Fine-grained Noise Filtering Mechanism for Retrieval-Augmented Large Language Models
- Blog: P3 Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning
- Blog: PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Models
- Blog: Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering
- Blog: M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions
- Blog: Unifying Generative and Dense Retrieval for Sequential Recommendation
- Blog: RELIC: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples
- Blog: The Power of Noise: Redefining Retrieval for RAG Systems
- Blog: InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filtering
Showing 60 of 129 papers.
History & citation
Current · Permanent link
- This direction split from Aligning Retrieval with Language Model Utility (77% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_relevance_utility_gap_c1f83ac0,
title = {relevance-utility gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/relevance-utility-gap/rdr_c1f83ac09d6d45f69f77c59bd468d1fc},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_relevance_utility_gap_c1f83ac0_v1,
title = {relevance-utility gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/relevance-utility-gap/rdr_c1f83ac09d6d45f69f77c59bd468d1fc/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}