multi-turn

2 items

RESEARCHarXiv CS.LG·4/21/2026

SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics

SaFeR-Steer is a novel framework designed to improve the safety alignment of Multi-modal Large Language Models (MLLMs) in multi-turn dialogues, addressing challenges like escalating unsafe intent and long-context safety decay. It employs synthetic bootstrapping and feedback dynamics, while also releasing the STEER dataset for training and evaluation.

Safety security MLLMs multi-turn

RESEARCHarXiv CS.AI·4/7/2026

TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering

TABQAWORLD é um novo framework para otimizar o raciocínio multimodal em perguntas e respostas sobre tabelas multi-turn. Ele aborda erros de representação e altos custos de inferência ao empregar uma política de seleção multimodal que alterna dinamicamente entre representações visuais e textuais para maximizar a confiabilidade do estado da tabela.

AI frameworks Table Question Answering Multimodal Reasoning multi-turn