AboutTopCourses
← heapsort-ai

Conversational AI

52 items

RESEARCHarXiv CS.CL·4/10/2026

EMSDialog: Synthetic Multi-person Emergency Medical Service Dialogue Generation from Electronic Patient Care Reports via Multi-LLM Agents

O estudo apresenta o EMSDialog, um novo conjunto de dados de 4.414 conversas sintéticas multi-falantes para serviços médicos de emergência, geradas a partir de relatórios reais de pacientes usando uma pipeline de agentes multi-LLM. Este dataset, anotado com diagnósticos e tópicos, demonstra melhorias na precisão e estabilidade da previsão de diagnóstico conversacional.

synthetic dialogue generationHealthcaremulti-LLM agentsmedical AI
27
RESEARCHarXiv CS.CL·5/8/2026

When2Speak: A Dataset for Temporal Participation and Turn-Taking in Multi-Party Conversations for Large Language Models

When2Speak is a new synthetic dataset and four-stage generation pipeline designed to teach Large Language Models (LLMs) appropriate intervention timing in multi-party conversations. It addresses the challenge of avoiding excessive interruptions and improving conversational coherence in group interactions.

LLMsmachine learningdatasetsConversational AI
27
RESEARCHarXiv CS.CL·25d ago

Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents

This research introduces Inquisitive Conversational Agents (ICAs) designed to proactively extract information, specifically tailored for U.S. Supreme Court oral arguments. It proposes a Dual Hierarchical Reinforcement Learning framework to coordinate strategic dialogue management and fine-grained utterance generation, significantly outperforming baselines.

reinforcement learninglegal techdialogue systemsConversational AI
27
RESEARCHarXiv CS.CL·28d ago

SalesSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators

SalesSim is a framework and testbed designed to evaluate Multimodal Large Language Models (MLLMs) as realistic, persona-driven customer simulators in online retail conversations. It models retail interaction as an agentic process, benchmarking state-of-the-art models and identifying behavioral gaps in decision alignment and conversational quality.

Retail AIUser SimulationBenchmarkingMultimodal Language Models
27