Moshi is the first real-time full-duplex spoken large language model that casts dialogue as speech-to-speech generation using parallel audio streams and an inner monologue of time-aligned text tokens.
Dialogpt: Large-scale generative pre-training for conversational response generation
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
DoctorAgent-RL trains a Qwen2.5-7B doctor agent via multi-agent RL on the new MTMedDialog dataset to conduct dynamic, question-driven consultations, reaching 70% exact diagnostic match in real-patient trials.
LaMDA shows that fine-tuning on human-value annotations and consulting external knowledge sources significantly improves safety and factual grounding in large dialog models beyond what scaling alone achieves.
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
CTGAN and LLMs generate synthetic student data that passes statistical and predictive utility checks for learning analytics.
A literature review that categorizes bias in LLMs, surveys evaluation and mitigation techniques, and discusses ethical implications.
citing papers explorer
-
Moshi: a speech-text foundation model for real-time dialogue
Moshi is the first real-time full-duplex spoken large language model that casts dialogue as speech-to-speech generation using parallel audio streams and an inner monologue of time-aligned text tokens.
-
Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning
DoctorAgent-RL trains a Qwen2.5-7B doctor agent via multi-agent RL on the new MTMedDialog dataset to conduct dynamic, question-driven consultations, reaching 70% exact diagnostic match in real-patient trials.
-
LaMDA: Language Models for Dialog Applications
LaMDA shows that fine-tuning on human-value annotations and consulting external knowledge sources significantly improves safety and factual grounding in large dialog models beyond what scaling alone achieves.
-
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
-
Creating Artificial Students that Never Existed: Leveraging Large Language Models and CTGANs for Synthetic Data Generation
CTGAN and LLMs generate synthetic student data that passes statistical and predictive utility checks for learning analytics.
-
Bias in Large Language Models: Origin, Evaluation, and Mitigation
A literature review that categorizes bias in LLMs, surveys evaluation and mitigation techniques, and discusses ethical implications.