会员服务
DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi
Arxiv
1+阅读 · 10月9日
Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky
Arxiv
0+阅读 · 10月9日
FedDTRE: Federated Dialogue Generation Models Powered by Trustworthiness Evaluation
Arxiv
0+阅读 · 10月9日
Confident-Knowledge Diversity Drives Human-Human and Human-AI Free Discussion Synergy and Reveals Pure-AI Discussion Shortfalls
Arxiv
0+阅读 · 10月9日
MADS: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation
Arxiv
0+阅读 · 9月30日
Prompt reinforcing for long-term planning of large language models
Arxiv
0+阅读 · 10月7日
When AI Gets Persuaded, Humans Follow: Inducing the Conformity Effect in Persuasive Dialogue
Arxiv
0+阅读 · 10月5日
ReactDiff: Fundamental Multiple Appropriate Facial Reaction Diffusion Model
Arxiv
0+阅读 · 10月6日
APIDA-Chat: Structured Synthesis of API Search Dialogues to Bootstrap Conversational Agents
Arxiv
0+阅读 · 10月4日
Non-Collaborative User Simulators for Tool Agents
Arxiv
0+阅读 · 10月6日
TeachLM: Post-Training LLMs for Education Using Authentic Learning Data
Arxiv
0+阅读 · 10月6日
MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators
Arxiv
0+阅读 · 10月6日
Triadic Multi-party Voice Activity Projection for Turn-taking in Spoken Dialogue Systems
Arxiv
0+阅读 · 10月3日
MIRROR: Modular Internal Processing for Personalized Safety in LLM Dialogue
Arxiv
0+阅读 · 10月3日
CLARITY: Clinical Assistant for Routing, Inference, and Triage
Arxiv
0+阅读 · 10月2日
参考链接
父主题
人机对话
微信扫码咨询专知VIP会员
Top