Related papers: The Use of Knowledge Preconditions in Language Pro…
With strong capabilities of reasoning and a broad understanding of the world, Large Language Models (LLMs) have demonstrated immense potential in building versatile embodied decision-making agents capable of executing a wide array of tasks.…
This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e.g., BERT, GPT-2/3), without human supervision. Popular KGs (e.g, Wikidata, NELL) are built in either a supervised or semi-supervised manner,…
The paper presents a knowledge representation formalism, in the form of a high-level Action Description Language for multi-agent systems, where autonomous agents reason and act in a shared environment. Agents are autonomously pursuing…
Understanding the dynamics of counseling conversations is an important task, yet it is a challenging NLP problem regardless of the recent advance of Transformer-based pre-trained language models. This paper proposes a systematic approach to…
This paper investigates pre-trained language models to find out which model intrinsically carries the most informative representation for task-oriented dialogue tasks. We approach the problem from two aspects: supervised classifier probe…
Personalizing dialogue agents is important for dialogue systems to generate more specific, consistent, and engaging responses. However, most current dialogue personalization approaches rely on explicit persona descriptions during inference,…
Discourse processing suffers from data sparsity, especially for dialogues. As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs). We investigate…
In biological systems, the capacity of anticipation--that is, entertaining a model of the system within the system--can be considered as naturally given. Human languages enable psychological systems to construct and exchange mental models…
In this paper, we propose Latent Relation Language Models (LRLMs), a class of language models that parameterizes the joint distribution over the words in a document and the entities that occur therein via knowledge graph relations. This…
To ensure readability, text is often written and presented with due formatting. These text formatting devices help the writer to effectively convey the narrative. At the same time, these help the readers pick up the structure of the…
Psychological and social systems provide us with a natural domain for the study of anticipations because these systems are based on and operate in terms of intentionality. Psychological systems can be expected to contain a model of…
In social systems, meaning can be communicated in addition to underlying processes of the information exchange. Meaning processing incurs on information processing with hindsight, while information processing recursively follows the time…
Deployed, autonomous AI systems must often evaluate multiple plausible courses of action (extended sequences of behavior) in novel or under-specified contexts. Despite extensive training, these systems will inevitably encounter scenarios…
Concurrent computations resemble conversations. In a conversation, participants direct utterances at others and, as the conversation evolves, exploit the known common context to advance the conversation. Similarly, collaborating software…
A large body of work in psycholinguistics has focused on the idea that online language comprehension can be shallow or `good enough': given constraints on time or available computation, comprehenders may form interpretations of their input…
World models, which encapsulate the dynamics of how actions affect environments, are foundational to the functioning of intelligent agents. In this work, we explore the potential of Large Language Models (LLMs) to operate as world models.…
Although many pretrained models exist for text or images, there have been relatively fewer attempts to train representations specifically for dialog understanding. Prior works usually relied on finetuned representations based on generic…
This paper presents a machine learning approach to discourse planning in natural language generation. More specifically, we address the problem of learning the most natural ordering of facts in discourse plans for a specific domain. We…
Complex, real-world domains may not be fully modeled for an agent, especially if the agent has never operated in the domain before. The agent's ability to effectively plan and act in such a domain is influenced by its knowledge of when it…
We study the ability of language models to reason about appropriate information disclosure - a central aspect of the evolving field of agentic privacy. Whereas previous works have focused on evaluating a model's ability to align with human…