Principled Context Engineering for RAG: StatisticalGuarantees via Conformal Prediction

This abstract has open access
Abstract Summary
Abstract ID :
NKDR110
Submission Type
Short papers
Submission Topics
Explainability methods Large Language Models Retrieval-Augmented Generation

Associated Sessions

Poster Session (Short Papers)
Debashish Chakraborty
Researcher
,
Johns Hopkins University
Eugene Yang
Research Scientist
,
Human Language Technology Center Of Excellence, Johns Hopkins University
Daniel Khashabi
Dr. Dawn Lawrie
Senior Research Scientist
,
HLTCOE At Johns Hopkins University
Kevin Duh
Johns Hopkins University Human Language Technology Center of Excellence (HLTCOE)

Abstracts With Same Type

Abstract ID
Abstract Title
Abstract Topic
Submission Type
Primary Author
NKDR99
Adversarial Edge Perturbation Framework in Graph-based Retrieval
Machine learning Search and ranking
Short papers
Mr. Amir Khosrojerdi
NKDR115
Aligning Instruction-Tuned LLMs for Event Extraction with Multi-objective Reinforcement Learning
IR applications Large Language Models
Short papers
Omar Adjali
NKDR208
Analyzing AI Evaluation Benchmarks Through InformationRetrieval and Network Science
IR evaluation
Short papers
Gaia Simeoni
NKDR108
Beyond Correlations: A Downstream Evaluation Framework forQuery Performance Prediction
IR evaluation Search and ranking
Short papers
Ms. PAYEL SANTRA
NKDR104
Beyond Persuasiveness: A User-Centric Evaluation Framework of Explanations for Food Recommendation
Short papers
Yurou Zhao
NKDR112
Controlling Gender Bias in Retrieval via a Backpack Architecture
Machine learning Search and ranking
Short papers
Amirabbas Afzali
NKDR118
Correct but Incomplete: Why Chain-of-Thought Cannot Currently Support Auditable Reasoning
IR evaluation
Short papers
Edward Richards
NKDR82
DARE: A Dialectical Framework for Adversarial and Evidence-Aware RAG
Generative IRIR applicationsLarge Language ModelsRetrieval-Augmented GenerationSystem aspects
Short papers
Saisab Sadhu
NKDR84
Do We Still Need Text for Video Retrieval in the Era of Vision-Language Models?
Short papers
Jiaqi Zhan
1 visits