Related papers: Predicting cross-linguistic adjective order with i…

Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. However, explanations on…

The set of finite words over a well-quasi-ordered set is itself well-quasi-ordered. This seminal result by Higman is a cornerstone of the theory of well-quasi-orderings and has found numerous applications in computer science. However, this…

Alignment of Large Language Models (LLMs) remains an unsolved problem. Human preferences are highly distributed and can be captured at multiple levels of abstraction, from the individual to diverse populations. Organisational preferences,…

In this paper, we investigate the phenomena of "selection biases" in Large Language Models (LLMs), focusing on problems where models are tasked with choosing the optimal option from an ordered sequence. We delve into biases related to…

The evaluative character of a word is called its semantic orientation. A positive semantic orientation implies desirability (e.g., "honest", "intrepid") and a negative semantic orientation implies undesirability (e.g., "disturbing",…

Pretrained large language models (LLMs) are becoming increasingly powerful and ubiquitous in mainstream applications such as being a personal assistant, a dialogue model, etc. As these models become proficient in deducing user preferences…

We propose a cognitively and linguistically motivated set of sorts for lexical semantics in a compositional setting: the classifiers in languages that do have such pronouns. These sorts are needed to include lexical considerations in a…

In this work we extend previous analyses of linguistic networks by adopting a multi-layer network framework for modelling the human mental lexicon, i.e. an abstract mental repository where words and concepts are stored together with their…

Multilingual Retrieval-Augmented Generation (mRAG) systems enable language models to answer knowledge-intensive queries with citation-supported responses across languages. While such systems have been proposed, an open questions is whether…

This paper investigates biases of Large Language Models (LLMs) through the lens of grammatical gender. Drawing inspiration from seminal works in psycholinguistics, particularly the study of gender's influence on language perception, we…

The next token prediction loss is the dominant self-supervised training objective for large language models and has achieved promising results in a variety of downstream tasks. However, upon closer investigation of this objective, we find…

Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This alignment process often requires only a small amount of data to…

Models of bags of words typically assume topic mixing so that the words in a single bag come from a limited number of topics. We show here that many sets of bag of words exhibit a very different pattern of variation than the patterns that…

Alignment of large language models remains a central challenge in natural language processing. Preference optimization has emerged as a popular and effective method for improving alignment, typically through training-time or prompt-based…

Large language models are often ranked according to their level of alignment with human preferences -- a model is better than other models if its outputs are more frequently preferred by humans. One of the popular ways to elicit human…

Most current NLP systems have little knowledge about quantitative attributes of objects and events. We propose an unsupervised method for collecting quantitative information from large amounts of web data, and use it to create a new, very…

While the reasoning abilities of large language models (LLMs) continue to advance, it remains unclear how such ability varies across languages in multilingual LLMs and whether different languages produce reasoning paths that complement each…

Object ranking or "learning to rank" is an important problem in the realm of preference learning. On the basis of training data in the form of a set of rankings of objects represented as feature vectors, the goal is to learn a ranking…

Recent research has demonstrated that large pre-trained language models reflect societal biases expressed in natural language. The present paper introduces a simple method for probing language models to conduct a multilingual study of…

One of the ultimate goals for linguists is to find universal properties in human languages. Although words are generally considered as representing arbitrary mapping between linguistic forms and meanings, we propose a new universal law that…