Language models that seek for knowledge: Modular search & generation for dialogue and prompt completion

K Shuster, M Komeili, L Adolphs, S Roller… - arxiv preprint arxiv …, 2022 - arxiv.org
Language models (LMs) have recently been shown to generate more factual responses by
employing modularity (Zhou et al., 2021) in combination with retrieval (Adolphs et al., 2021) …

Dialogue chain-of-thought distillation for commonsense-aware conversational agents

H Chae, Y Song, KT Ong, T Kwon, M Kim, Y Yu… - arxiv preprint arxiv …, 2023 - arxiv.org
Human-like chatbots necessitate the use of commonsense reasoning in order to effectively
comprehend and respond to implicit information present within conversations. Achieving …

Towards faithful dialogues via focus learning

Y Deng, X Zhang, HY Huang, Y Hu - … of the 61st Annual Meeting of …, 2023 - aclanthology.org
Maintaining faithfulness between responses and knowledge is an important research topic
for building reliable knowledge-grounded dialogue systems. Existing models heavily rely on …

Comfact: A benchmark for linking contextual commonsense knowledge

S Gao, JD Hwang, S Kanno, H Wakaki… - arxiv preprint arxiv …, 2022 - arxiv.org
Understanding rich narratives, such as dialogues and stories, often requires natural
language processing systems to access relevant knowledge from commonsense knowledge …

Mind the gap! injecting commonsense knowledge for abstractive dialogue summarization

S Kim, SJ Joo, H Chae, C Kim, S Hwang… - arxiv preprint arxiv …, 2022 - arxiv.org
In this paper, we propose to leverage the unique characteristics of dialogues sharing
commonsense knowledge across participants, to resolve the difficulties in summarizing …

Generative commonsense knowledge subgraph retrieval for open-domain dialogue response generation

S Wu, J Yu, J Chen, W Zhou - Neural Networks, 2024 - Elsevier
Grounding on a commonsense knowledge subgraph can help the model generate more
informative and diverse dialogue responses. Prior Traverse-based works explicitly retrieve a …

ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI

SE Finch, JD Choi - Transactions of the Association for Computational …, 2024 - direct.mit.edu
Mastering commonsense understanding and reasoning is a pivotal skill essential for
conducting engaging conversations. While there have been several attempts to create …

A Textual Dataset for Situated Proactive Response Selection

N Otani, J Araki, HS Kim, E Hovy - … of the 61st Annual Meeting of …, 2023 - aclanthology.org
Recent data-driven conversational models are able to return fluent, consistent, and
informative responses to many kinds of requests and utterances in task-oriented scenarios …

Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems

SE Finch, JD Finch, JD Choi - arxiv preprint arxiv:2212.09180, 2022 - arxiv.org
Despite tremendous advancements in dialogue systems, stable evaluation still requires
human judgments producing notoriously high-variance metrics due to their inherent …

Newsdialogues: Towards proactive news grounded conversation

S Li, Y Yin, C Yang, W Jiang, Y Li, Z Cheng… - arxiv preprint arxiv …, 2023 - arxiv.org
Hot news is one of the most popular topics in daily conversations. However, news grounded
conversation has long been stymied by the lack of well-designed task definition and scarce …