This paper evaluates the performance of a Large Language Model (LLM) in a high-stakes context by comparing it to human experts and measuring variance and error magnitude.

This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.

This paper proposes a framework for multi-hop retrieval as query-set compatibility scoring, improving retrieval performance and downstream QA task performance.

The paper introduces FRANZ, a communicative audit framework, to evaluate how LLMs frame responses to subjective questions, finding that LLMs exhibit statistically significant and coupled differences i…

This paper evaluates the performance of large language models on quiz-style questions covering common and niche topics in six European languages, finding significant knowledge gaps and language-depend…

The paper proposes CheckRLM, a framework that improves the reliability of Reasoning Language Models by identifying and correcting factual errors using Retrieval-Augmented Generation.

The paper introduces OCC-RAG, a family of compact, task-specialized Small Language Models (SLMs) designed to achieve highly faithful, multi-hop question answering grounded strictly in provided context…

DS@GT ARC evaluates the effectiveness of Corrective RAG (CRAG) and CiteFix in improving citation faithfulness and answer grounding in Retrieval-Augmented Generation (RAG) QA systems, revealing a trade…

The paper systematically compares multiple content representations for RAG pipelines and finds that answer retention—the ability of the representation to preserve the original answer-bearing content—i…

This paper introduces AB-RAG, a training-free and backbone-agnostic framework for adaptively generating answers, estimating their confidence, and deciding whether to retrieve more evidence based on th…

The paper proposes using question-asking as an inference-time intervention to probe a language model's hidden state, finding that the self-diagnosis process provides a predictive signal for final corr…

This paper investigates how the final prompt in conversational AI-search evaluations differs from the conversation history, using two corpora of commercial and PRISM conversations.

The paper introduces RefMem-Bench, a new benchmark for measuring reflective memory in long-horizon dialogue, and proposes REMIND, a framework that significantly improves models' ability to synthesize…

SPADER is a novel reinforcement learning framework that addresses the challenges of Multi-Answer Question Answering by improving credit assignment and promoting diverse exploration during long-horizon…

The paper introduces RHELM, a new benchmark designed to test LLMs' long-term memory by simulating realistic, complex, and evolving dialogues that integrate multiple heterogeneous data sources.

This paper introduces Audio-Dependency Filtering (ADF) pipeline for Audio-Dependent Question Answering (ADQA) task in DCASE~2026, achieving top overall and sub-10B accuracy.

The paper compares verbalized feature attributions and self-generated rationales for explaining model behavior, finding that the format and granularity of the explanation significantly affect its abil…

CA-BED is a novel framework that improves LLM performance in interactive question-answering by integrating Bayesian Experimental Design to strategically select questions that maximize information gain…

The paper introduces RUMBA, a new benchmark for long-term conversational memory in LLMs with a fine-grained taxonomy and unified methodology.