https://github.com/facebookresearch/fnctod
공식 코드Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
A task where an agent should play the $DE$ role and generate a text to respond to a $P$ message.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation
ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers
The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG)
Aligning LLM Agents by Learning Latent Preference from User Edits
UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue
Survey on Abstractive Text Summarization: Dataset, Models, and Metrics
Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report
Zero-shot Cross-lingual Conversational Semantic Role Labeling
Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation
Group-wise Contrastive Learning for Neural Dialogue Generation
Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems
Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters
CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
Topic-Aware Response Generation in Task-Oriented Dialogue with Unstructured Knowledge Access
ELF22: A Context-based Counter Trolling Dataset to Combat Internet Trolls
CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models
Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog
GINGER: Grounded Information Nugget-Based Generation of Responses
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.