Related papers: A Solution to Yamakami's Problem on Advised Contex…

Recently, large language models (LLMs) (e.g., GPT-4) have demonstrated impressive general-purpose task-solving abilities, including the potential to approach recommendation tasks. Along this line of research, this work aims to investigate…

We analyze a word embedding method in supervised tasks. It maps words on a sphere such that words co-occurring in similar contexts lie closely. The similarity of contexts is measured by the distribution of substitutes that can fill them. We…

Language models (LLMs) offer potential as a source of knowledge for agents that need to acquire new task competencies within a performance environment. We describe efforts toward a novel agent capability that can construct cues (or…

Regular languages (RL) are the simplest family in Chomsky's hierarchy. Thanks to their simplicity they enjoy various nice algebraic and logic properties that have been successfully exploited in many application fields. Practically all of…

As the latest advancements in natural language processing, large language models (LLMs) have achieved human-level language understanding and generation abilities in many real-world tasks, and even have been regarded as a potential path to…

A prefix code L satisfies the condition that no word of L is a proper prefix of another word of L. Recently, Ko, Han and Salomaa relaxed this condition by allowing a word of L to be a proper prefix of at most k words of L, for some `margin'…

Let L denote the class Logpsace and NL the class NLogspace. We use logCFL to denote the closure under logspace reductions of the set of context-free languages. We prove that NL is different from logCFL. This result implies L different from…

Large language models (LLMs) have exhibited impressive multilingual reasoning capabilities, driven by extensive multilingual pre-training corpora and instruction fine-tuning data. However, a performance gap exists between high- and…

Automatically generating high-quality step-by-step solutions to math word problems has many applications in education. Recently, combining large language models (LLMs) with external tools to perform complex reasoning and calculation has…

Training Large Language Models (LLMs) with high multilingual coverage is becoming increasingly important -- especially when monolingual resources are scarce. Recent studies have found that LLMs process multilingual inputs in shared concept…

Active context-free games are two-player games on strings over finite alphabets with one player trying to rewrite the input string to match a target specification. These games have been investigated in the context of exchanging Active XML…

Humans can easily tell if an attribute (also called state) is realistic, i.e., feasible, for an object, e.g. fire can be hot, but it cannot be wet. In Open-World Compositional Zero-Shot Learning, when all possible state-object combinations…

We present a novel approach to formalise and solve search-based problems using large language models, which significantly improves upon previous state-of-the-art results. We demonstrate the efficacy of this approach on the logic puzzles…

In this study, we propose a structured methodology that utilizes large language models (LLMs) in a cost-efficient and parsimonious manner, integrating the strengths of scholars and machines while offsetting their respective weaknesses. Our…

Language models (LMs) show state of the art performance for common sense (CS) question answering, but whether this ability implies a human-level mastery of CS remains an open question. Understanding the limitations and strengths of LMs can…

Large language models (LLMs) have demonstrated high performance on tasks expressed in natural language, particularly in zero- or few-shot settings. These are typically framed as supervised (e.g., classification) or unsupervised (e.g.,…

We investigate two problems for a class C of regular word languages. The C-membership problem asks for an algorithm to decide whether an input language belongs to C. The C-separation problem asks for an algorithm that, given as input two…

We present a new approach to formal language theory using Kolmogorov complexity. The main results presented here are an alternative for pumping lemma(s), a new characterization for regular languages, and a new method to separate…

Progress in long-context reasoning for large language models (LLMs) has lagged behind other recent advances. This gap arises not only from the intrinsic difficulty of processing long texts, but also from the scarcity of reliable human…

Word class flexibility refers to the phenomenon whereby a single word form is used across different grammatical categories. Extensive work in linguistic typology has sought to characterize word class flexibility across languages, but…