Question Answering

Test-time scaling + confidence = better QA!

SAFE-SQL boosts Text-to-SQL accuracy by intelligently generating and filtering self-augmented examples for in-context learning, surpassing existing methods in challenging scenarios.

SQUARE, a novel prompting technique, enhances LLM reasoning by prompting self-interrogation through sequential question answering, significantly outperforming traditional methods.

Fact-checkers need explainable AI: This study reveals how AI tools can better support fact-checkers by providing explanations tailored to their workflows, addressing unmet needs, and improving the eff…

FailSafeQA benchmark rigorously evaluates LLMs’ resilience against diverse human-interaction variations, revealing critical weaknesses in even high-performing models, particularly regarding hallucinat…

ARR: A novel zero-shot prompting method significantly boosts LLM performance on diverse question-answering tasks by explicitly incorporating question analysis, information retrieval, and step-by-step …

DeepRAG enhances LLM reasoning by strategically integrating retrieval, modeled as an MDP, improving accuracy by 21.99% and retrieval efficiency.

ChartCitor: A multi-agent LLM framework combats LLM hallucination in ChartQA by providing fine-grained visual citations, enhancing user trust and productivity.

CoRAG, a novel Chain-of-Retrieval Augmented Generation model, dynamically refines queries for improved accuracy in multi-hop question answering, achieving state-of-the-art performance.

MMVU: a new benchmark pushes multimodal video understanding to expert level, revealing limitations of current models and paving the way for more advanced AI.

GeAR, a new retrieval model, boosts accuracy by combining document retrieval with fine-grained information generation, leading to better understanding and improved localization.

MAPQATOR: a web app that streamlines creation of reproducible geospatial QA datasets, boosting annotation speed by 30x!

OmniEval: Automatic benchmark for evaluating financial RAG systems.

RetroLLM unifies retrieval & generation in LLMs, boosting accuracy and cutting costs.

MedRGB benchmark reveals current LLMs struggle with noisy medical data, emphasizing the need for robust RAG systems in healthcare AI.

M-LongDoc: a new benchmark and retrieval-aware tuning framework revolutionizes multimodal long document understanding, improving model accuracy by 4.6%.

HtmlRAG boosts RAG system accuracy by using HTML, not plain text, to model retrieved knowledge, improving knowledge representation and mitigating LLM hallucination.

GRS-QA: New benchmark dataset reveals LLM reasoning limitations!