Cover Image

Improving Consistency in Retrieval-Augmented Systems with Group Similarity Rewards

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hamman, Faisal, Zhu, Chenyang, Kumar, Anoop, Peng, Xujun, Dutta, Sanghamitra, Liu, Daben, Samuel, Alfy
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Computers and Society Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Unified View of Group Fairness Tradeoffs Using Partial Information Decomposition
by: Hamman, Faisal, et al.
Published: (2024)

A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation
by: Lawton, Neal Gregory, et al.
Published: (2025)

Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
by: Hamman, Faisal, et al.
Published: (2023)

Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations
by: Hamman, Faisal, et al.
Published: (2025)

FB-RAG: Improving RAG with Forward and Backward Lookup
by: Chawla, Kushal, et al.
Published: (2025)

Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation
by: Huang, Zhiqi, et al.
Published: (2025)

Harmonizing Diverse Models: A Layer-wise Merging Strategy for Consistent Generation
by: Peng, Xujun, et al.
Published: (2025)

Quantifying Prediction Consistency Under Fine-Tuning Multiplicity in Tabular LLMs
by: Hamman, Faisal, et al.
Published: (2024)

LLM Optimization Unlocks Real-Time Pairwise Reranking
by: Wu, Jingyu, et al.
Published: (2025)

Readability Reconsidered: A Cross-Dataset Analysis of Reference-Free Metrics
by: Belem, Catarina G, et al.
Published: (2025)

Counterfactual Explanations for Model Ensembles Using Entropic Risk Measures
by: Noorani, Erfaun, et al.
Published: (2025)

Play by the Type Rules: Inferring Constraints for LLM Functions in Declarative Programs
by: Glenn, Parker, et al.
Published: (2025)

Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
by: Jain, Neel, et al.
Published: (2024)

Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
by: Hamman, Faisal, et al.
Published: (2023)

Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
by: Hu, Mengxuan, et al.
Published: (2026)

Towards Formalizing Spuriousness of Biased Datasets Using Partial Information Decomposition
by: Halder, Barproda, et al.
Published: (2024)

Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
by: Bakman, Yavuz, et al.
Published: (2025)

Can AI Debias the News? LLM Interventions Improve Cross-Partisan Receptivity but LLMs Overestimate Their Own Effectiveness
by: Feroz, Faisal, et al.
Published: (2026)

CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generation
by: Hou, Abe Bohan, et al.
Published: (2024)

Leveraging Lecture Content for Improved Feedback: Explorations with GPT-4 and Retrieval Augmented Generation
by: Jacobs, Sven, et al.
Published: (2024)

Improving Socratic Question Generation using Data Augmentation and Preference Optimization
by: Kumar, Nischal Ashok, et al.
Published: (2024)

Improving Assessment of Tutoring Practices using Retrieval-Augmented Generation
by: Han, Zifei FeiFei, et al.
Published: (2024)

VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation
by: Egea, David, et al.
Published: (2025)

BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents
by: Myakala, Praveen Kumar, et al.
Published: (2026)

DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation
by: Khan, Saadat Hasan, et al.
Published: (2026)

ConFit: Improving Resume-Job Matching using Data Augmentation and Contrastive Learning
by: Yu, Xiao, et al.
Published: (2024)

TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs
by: Yaldiz, Duygu Nur, et al.
Published: (2025)

Down the Toxicity Rabbit Hole: A Novel Framework to Bias Audit Large Language Models
by: Dutta, Arka, et al.
Published: (2023)

From Facts to Conclusions : Integrating Deductive Reasoning in Retrieval-Augmented LLMs
by: Mishra, Shubham, et al.
Published: (2025)

Online Anti-sexist Speech: Identifying Resistance to Gender Bias in Political Discourse
by: Dutta, Aditi, et al.
Published: (2025)

Is Self-knowledge and Action Consistent or Not: Investigating Large Language Model's Personality
by: Ai, Yiming, et al.
Published: (2024)

A Multilingual Similarity Dataset for News Article Frame
by: Chen, Xi, et al.
Published: (2024)

Ancient Wisdom, Modern Tools: Exploring Retrieval-Augmented LLMs for Ancient Indian Philosophy
by: Mandikal, Priyanka
Published: (2024)

Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
by: Dissanayake, Pasan, et al.
Published: (2024)

Divided by discipline? A systematic literature review on the quantification of online sexism and misogyny using a semi-automated approach
by: Dutta, Aditi, et al.
Published: (2024)

Towards Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward Models
by: Song, Kefan, et al.
Published: (2025)

T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning
by: Fu, Yanjun, et al.
Published: (2025)

LAPIS: Language Model-Augmented Police Investigation System
by: Kim, Heedou, et al.
Published: (2024)

TabDistill: Distilling Transformers into Neural Nets for Few-Shot Tabular Classification
by: Dissanayake, Pasan, et al.
Published: (2025)

Gender Representation and Bias in Indian Civil Service Mock Interviews
by: Banerjee, Somonnoy, et al.
Published: (2024)