arXiv AI October 27, 2026 By Jaeyoung Park, Hantian Zhang, Kexin Rong, Steven Euijong Whang

Topic-Level Fairness in Retrieval-Augmented Generation

The paper investigates topic-level fairness in retrieval‑augmented generation (RAG) systems, noting that aggregate metrics can mask disparities across individual topics. It proposes adapting a reranker per topic using a Bradley‑Terry objective guided by preference pairs derived from the generator’s own output, which reduces mean absolute per‑topic disparity by 51% on RoMQA and 40% on TREC Fair Ranking while preserving accuracy. Existing baselines, even when modified to treat topics separately, fail to achieve comparable reductions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Oct 7

Aggregating User Preferences while Ensuring Equity, Diversity, and Inclusion using Graph Summarization

arXiv:2610.07128v1 Announce Type: cross Abstract: Aggregating the preferences of diverse user groups into a collective outcome raises fundamental challenges of equity, diversity, and inclusion (EDI):...

By Adji Marieme Sita Ciss\'e, Malek Mouhoub

rag nlp safety

arXiv Machine Learning

Jun 26

Scoring Is Not Enough: Addressing Gaps in Utility-fairness Trade-offs for Ranking

arXiv:2606. 26369v1 Announce Type: cross Abstract: Scoring functions are used to represent the relevance of individual documents.

By Shubham Singh, Ian A. Kash, Mesrob I. Ohannessian

safety

arXiv Computation and Language

Oct 9

Fair-GPTQ: Bias-Aware Quantization for Large Language Models

Fair-GPTQ is a quantization method for large language models that incorporates explicit group‑fairness constraints into the quantization objective. By guiding the rounding operation, it reduces bias in generated text, particularly for occupational stereotypes and discriminatory language across gender, race, and religion. The approach maintains at least 90 % of baseline accuracy on zero‑shot benchmarks while preserving the memory and speed benefits of 4‑bit quantization.

By Irina Proskurina, Guillaume Metzler, Julien Velcin

llms efficiency benchmarks safety

arXiv AI

Jun 30

The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents

arXiv:2606. 28343v1 Announce Type: cross Abstract: Retrieval-augmented generative agents rely on retrieval for grounding, yet are typically evaluated on a query-by-query basis.

By Shwan Ashrafi, Dan Roth

rag agents safety

arXiv Computation and Language

Aug 25

WARP: Wasserstein-Aligned RAG for Population Opinions

arXiv:2608.22859v1 Announce Type: cross Abstract: RAG systems are increasingly used to summarize what large collections of documents say. A user asks "What do people think about X?" and receives an a...

By Aman Singh Thakur, Aditya Agrawal, Alwarappan Nakkiran, Alex Karlsson

llms rag

arXiv Machine Learning

Jun 9

Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints

arXiv:2601. 23221v2 Announce Type: replace Abstract: As acquiring reliable ground-truth labels is usually costly, or infeasible, crowdsourcing and aggregation of noisy human annotations is the typical resort.

By Gabriel Singer, Samuel Gruffaz, Olivier Vo Van, Nicolas Vayatis, Argyris Kalogeratos

benchmarks safety