相关论文: Predicting cross-linguistic adjective order with i…

Preference-based reinforcement learning (PbRL) is the dominant framework for aligning AI systems to human preferences. However, evaluation protocols for such data were designed for text and have not been validated for speech. We present the…

What mechanisms underlie linguistic generalization in large language models (LLMs)? This question has attracted considerable attention, with most studies analyzing the extent to which the language skills of LLMs resemble rules. As of yet,…

Eliciting information to reduce uncertainty about a latent entity is a critical task in many application domains, e.g., assessing individual student learning outcomes, diagnosing underlying diseases, or learning user preferences. Though…

Subjective well-being is a key metric in economic, medical, and policy decision-making. As artificial intelligence provides scalable tools for modelling human outcomes, it is crucial to evaluate whether large language models (LLMs) can…

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…

We address the linguistic problem of the sequential arrangement of a head and its dependents from an information theoretic perspective. In particular, we consider the optimal placement of a head that maximizes the predictability of the…

Modern language models are typically trained over subword sequences, but ultimately define probabilities over character-strings. Ideally, the choice of the tokeniser -- which maps character-strings to subwords -- should not affect the…

This study introduces a prescriptive annotation benchmark grounded in humanities research to ensure consistent, unbiased labeling of offensive language, particularly for casual and non-mainstream language uses. We contribute two newly…

Preference mechanisms, such as human preference, LLM-as-a-Judge (LaaJ), and reward models, are central to aligning and evaluating large language models (LLMs). Yet, the underlying concepts that drive these preferences remain poorly…

Studies of reinforcement learning in humans and animals have demonstrated a preference for options that yielded relatively better outcomes in the past, even when those options are associated with lower absolute reward. The present study…

Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks. These language models are almost universally autoregressive in nature, generating…

In lexicon-based classification, documents are assigned labels by comparing the number of words that appear from two opposed lexicons, such as positive and negative sentiment. Creating such words lists is often easier than labeling…

Word alignment is an important natural language processing task that indicates the correspondence between natural languages. Recently, unsupervised learning of log-linear models for word alignment has received considerable attention as it…

Large language models (LLMs) not only exhibit human-like performance but also share computational principles with the brain's language processing mechanisms. While prior research has focused on mapping LLMs' internal representations to…

This paper explores the space of (propositional) probabilistic logical languages, ranging from a purely `qualitative' comparative language to a highly `quantitative' language involving arbitrary polynomials over probability terms. While…

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

We use large language models to aid learners enhance proficiency in a foreign language. This is accomplished by identifying content on topics that the user is interested in, and that closely align with the learner's proficiency level in…

We propose a multilingual model to recognize Big Five Personality traits from text data in four different languages: English, Spanish, Dutch and Italian. Our analysis shows that words having a similar semantic meaning in different languages…

Human languages have evolved to be structured through repeated language learning and use. These processes introduce biases that operate during language acquisition and shape linguistic systems toward communicative efficiency. In this paper,…

Written language is a complex communication signal capable of conveying information encoded in the form of ordered sequences of words. Beyond the local order ruled by grammar, semantic and thematic structures affect long-range patterns in…