In this paper, we introduce VerifiNER, a post-hoc verification framework that identifies errors from existing NER methods using knowledge and revises them into more faithful predictions.

In this paper, we propose a code editing model that succesfully fix bugs in given code leveraging feedback.

In this paper, we introduce DOCTOR, a DialOgue Chain-of-ThOught Reasoner that provides reliable CoT rationales for response generation.

In this paper, we propose Tutoring bot, a generative chatbot trained on a large scale of tutor-student conversations for English-language learning.

In this paper, we introduce CoTEVer, a tool-kit for annotating the factual correctness of generated explanations and collecting revision data of wrong explanations.

In this paper, we propose to leverage the unique characteristics of dialogues sharing commonsense knowledge across participants, to resolve the difficulties in summarizing them.