arXiv AI June 6, 2026 By Aditya Agrawal, Alwarappan Nakkiran, Darshan Fofadiya, Alex Karlsson, Harsha Aduri

Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions

arXiv:2604. 12138v2 Announce Type: replace Abstract: This position paper argues that Retrieval-Augmented Generation systems exhibit a systematic factual bias-optimizing for epistemic uncertainty reduction while ignoring the aleatoric uncertainty inherent in opinion-rich content - and that this misalignment demands a paradigm shift in retrieval system design.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

2d ago

Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact

arXiv:2608. 13926v1 Announce Type: new Abstract: Large language models have made natural language interfaces to databases (NLIDB) newly credible, but LLM text-to-SQL systems fail in a way that matters for deployment: a hallucinated column or a mis-aggregated total yields a fluent wrong answer, indistinguishable at the point of use from a right one.

By Zhelun (Allen), Wu

llms agents fine-tuning benchmarks data-engineering

arXiv AI

Jul 14

Large Language Models for Token-Efficient and Semantic-Preserving Opinion Summarization

arXiv:2607. 10825v1 Announce Type: cross Abstract: Opinionated text - spanning product reviews, hotel feedback, and social posts - captures rich signals about user experiences, preferences, and concerns.

By Fabrizio Marozzo, Stefano Iannicelli

llms nlp

arXiv AI

1d ago

When AI Rewrites, Classifiers Relax: Uncertainty-Aware Sentiment Analysis on Sarcastic and AI-Paraphrased Social Text

arXiv:2608. 15338v1 Announce Type: cross Abstract: Sentiment classifiers are increasingly applied to social media content that is either sarcastic or AI-generated --- two distributional regimes where standard evaluations offer little guidance.

By Shresth Shroff

nlp safety

arXiv AI

Jul 1

SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA

arXiv:2504. 07385v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly used for question-answering (QA), relying on static, pre-annotated references for evaluation poses significant challenges in cost, scalability, and completeness.

By Sher Badshah, Ali Emami, Hassan Sajjad

llms agents benchmarks

arXiv AI

Jul 16

With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots

arXiv:2602. 09616v2 Announce Type: replace-cross Abstract: Reliable retrieval-augmented generation (RAG) systems depend fundamentally on the retriever's ability to find relevant information.

By Zeinab Sadat Taghavi, Ali Modarressi, Hinrich Schutze, Andreas Marfurt

rag

arXiv AI

Jun 2

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation

arXiv:2606. 01212v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are widely deployed and increasingly influential, but their reliance on external corpora exposes new security risks from poisoned retrieval content.

By Yuyang Gong, Miaokun Chen, Jiawei Liu, Zhuo Chen, Guoxiu He, Wei Lu, XiaoFeng Wang, Xiaozhong Liu

rag agents robotics

Related stories

Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact

Large Language Models for Token-Efficient and Semantic-Preserving Opinion Summarization

When AI Rewrites, Classifiers Relax: Uncertainty-Aware Sentiment Analysis on Sarcastic and AI-Paraphrased Social Text

SAGE: A Search-AuGmented Evaluation of Large Language Models on Free-Form QA

With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation