paper-with-me

홈 › Papers

CorrectionLM: Self-Corrections with SLM for Dialogue State Tracking

2024-10-23 · Chia-Hsuan Lee, Hao Cheng, Mari Ostendorf

Large language models (LLMs) have demonstrated self-improvement capabilities via feedback and refinement, but current small language models (SLMs) have had limited success in this area. Existing correction approaches often rely on distilling knowledge from LLMs, which imposes significant computation demands. In this work, we introduce CORRECTIONLM, a novel correction framework that enables SLMs to self-correct using in-context exemplars without LLM involvement. Applied to two dialogue state tracking (DST) tasks in low-resource settings, CORRECTIONLM achieves results similar to a state-of-the-art LLM at a small fraction of the computation costs.

📄 PDF Abstract BibTeX arXiv:2410.18209

Code (0)

등록된 구현이 없습니다.

Tasks

Dialogue State Tracking

Similar Papers 제목 키워드 기반

MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines

2020-07-10 · WS 2020 7 · Xiaoxue Zang, Abhinav Rastogi, Srinivas Sunkara, Raghav Gupta 외

MultiWOZ is a well-known task-oriented dialogue dataset containing over 10,000 annotated dialogues spanning 8 domains. It is extensively used as a benchmark for dialogue state tracking. However, recent works have reporte…

Dialogue State Tracking

MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines

2019-07-02 · LREC 2020 5 · Mihail Eric, Rahul Goel, Shachi Paul, Adarsh Kumar 외

MultiWOZ 2.0 (Budzianowski et al., 2018) is a recently released multi-domain dialogue dataset spanning 7 distinct domains and containing over 10,000 dialogues. Though immensely useful and one of the largest resources of …

Dialogue State TrackingMulti-domain Dialogue State Tracking

Multi-Domain Dialogue State Tracking with Top-K Slot Self Attention

2022-09-01 · SIGDIAL (ACL) 2022 9 · Longfei Yang, Jiyi Li, Sheng Li, Takahiro Shinozaki

As an important component of task-oriented dialogue systems, dialogue state tracking is designed to track the dialogue state through the conversations between users and systems. Multi-domain dialogue state tracking is a …

Dialogue State TrackingMulti-domain Dialogue State TrackingTask-Oriented Dialogue Systems

MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation

2021-04-01 · SIGDIAL (ACL) 2022 9 · Fanghua Ye, Jarana Manotumruksa, Emine Yilmaz

The MultiWOZ 2.0 dataset has greatly stimulated the research of task-oriented dialogue systems. However, its state annotations contain substantial noise, which hinders a proper evaluation of model performance. To address…

Dialogue State TrackingTask-Oriented Dialogue Systems

MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation

2020-10-12 · Ting Han, Ximing Liu, Ryuichi Takanobu, Yixin Lian 외

Task-oriented dialogue systems have made unprecedented progress with multiple state-of-the-art (SOTA) models underpinned by a number of publicly available MultiWOZ datasets. Dialogue state annotations are error-prone, le…

Dialogue State TrackingNatural Language UnderstandingTask-Oriented Dialogue Systems