Language models that seek for knowledge: Modular search & generation for dialogue and prompt completion
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) …
employing modularity (Zhou et al., 2021) in combination with retrieval (Adolphs et al., 2021) …
Dialogue chain-of-thought distillation for commonsense-aware conversational agents
Human-like chatbots necessitate the use of commonsense reasoning in order to effectively
comprehend and respond to implicit information present within conversations. Achieving …
comprehend and respond to implicit information present within conversations. Achieving …
Towards faithful dialogues via focus learning
Maintaining faithfulness between responses and knowledge is an important research topic
for building reliable knowledge-grounded dialogue systems. Existing models heavily rely on …
for building reliable knowledge-grounded dialogue systems. Existing models heavily rely on …
Comfact: A benchmark for linking contextual commonsense knowledge
Understanding rich narratives, such as dialogues and stories, often requires natural
language processing systems to access relevant knowledge from commonsense knowledge …
language processing systems to access relevant knowledge from commonsense knowledge …
Mind the gap! injecting commonsense knowledge for abstractive dialogue summarization
In this paper, we propose to leverage the unique characteristics of dialogues sharing
commonsense knowledge across participants, to resolve the difficulties in summarizing …
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 …
informative and diverse dialogue responses. Prior Traverse-based works explicitly retrieve a …
ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI
Mastering commonsense understanding and reasoning is a pivotal skill essential for
conducting engaging conversations. While there have been several attempts to create …
conducting engaging conversations. While there have been several attempts to create …
A Textual Dataset for Situated Proactive Response Selection
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 …
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
Despite tremendous advancements in dialogue systems, stable evaluation still requires
human judgments producing notoriously high-variance metrics due to their inherent …
human judgments producing notoriously high-variance metrics due to their inherent …
Newsdialogues: Towards proactive news grounded conversation
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 …
conversation has long been stymied by the lack of well-designed task definition and scarce …