Related papers: Language and Temporal Aspects: A Qualitative Study…
Motivation is a central driver of human behavior, shaping decisions, goals, and task performance. As large language models (LLMs) become increasingly aligned with human preferences, we ask whether they exhibit something akin to motivation.…
We analyze reasoning in language models during task-specific fine-tuning and draws parallel between reasoning tokens--intermediate steps generated while solving problem and the human working memory. Drawing from cognitive science, we align…
It is desirable for an agent to be able to solve a rich variety of problems that can be specified through language in the same environment. A popular approach towards obtaining such agents is to reuse skills learned in prior tasks to…
Value trade-offs are an integral part of human decision-making and language use, however, current tools for interpreting such dynamic and multi-faceted notions of values in language models are limited. In cognitive science, so-called…
In this paper, we introduce the action language C-MT (Mind Transition Language). It is built on top of answer set programming (ASP) and transition systems to represent how human mental states evolve in response to sequences of observable…
In our world with full of uncertainty, debates and argumentation contribute to the progress of science and society. Despite of the increasing attention to characterize human arguments, most progress made so far focus on the debate outcome,…
Cross-situational word learning, wherein a learner combines information about possible meanings of a word across multiple exposures, has previously been shown to be a very powerful strategy to acquire a large lexicon in a short time.…
Choice decisions made by users of online applications can suffer from biases due to the users' level of engagement. For instance, low engagement users may make random choices with no concern for the quality of items offered. This biased…
We investigate neural models' ability to capture lexicosyntactic inferences: inferences triggered by the interaction of lexical and syntactic information. We take the task of event factuality prediction as a case study and build a…
Temporal logic rules are often used in control and robotics to provide structured, human-interpretable descriptions of trajectory data. These rules have numerous applications including safety validation using formal methods, constraining…
Reasoning is a key ability for an intelligent system. Large language models (LMs) achieve above-chance performance on abstract reasoning tasks, but exhibit many imperfections. However, human abstract reasoning is also imperfect. For…
Neuroscientists formulate very different hypotheses about the nature of neural code. At one extreme, it has been argued that neurons encode information in relatively slow changes of individual spikes arriving "rates codes" and the…
This study investigates the causal neural dynamics by which affordance representations influence action language comprehension. In this study, 18 participants observed stimuli displayed in two conditions during the experiment: text-only…
Large language models have shown that impressive zero-shot performance can be achieved through natural language prompts (Radford et al., 2019; Brown et al., 2020; Sanh et al., 2021). Creating an effective prompt, however, requires…
While the ability of language models to elicit facts has been widely investigated, how they handle temporally changing facts remains underexplored. We discover Temporal Heads, specific attention heads that primarily handle temporal…
Does the effectiveness of neural language models derive entirely from accurate modeling of surface word co-occurrence statistics, or do these models represent and reason about the world they describe? In BART and T5 transformer language…
Rules in logic programming encode information about mutual interdependencies between literals that is not captured by any of the commonly used semantics. This information becomes essential as soon as a program needs to be modified or…
Impulsive individuals exhibit abnormal reward processing (heightened preference for immediate rewards, i.e., impulsive choice, IC) and a penchant for maladaptive action (the inability to inhibit inappropriate actions, i.e., impulsive…
Causal games are probabilistic graphical models that enable causal queries to be answered in multi-agent settings. They extend causal Bayesian networks by specifying decision and utility variables to represent the agents' degrees of freedom…
Following the initial excitement, Text-to-Image (TTI) models are now being examined more critically. While much of the discourse has focused on biases and stereotypes embedded in large-scale training datasets, the sociotechnical dynamics of…