Related papers: NumeroLogic: Number Encoding for Enhanced LLMs' Nu…

Recent developments in reasoning capabilities have enabled large language models to solve increasingly complex mathematical, symbolic, and logical tasks. Interestingly, while reasoning models are often trained to generate monolingual text,…

Causal reasoning, the ability to identify cause-and-effect relationship, is crucial in human thinking. Although large language models (LLMs) succeed in many NLP tasks, it is still challenging for them to conduct complex causal reasoning…

We present a new approach to termination analysis of numerical computations in logic programs. Traditional approaches fail to analyse them due to non well-foundedness of the integers. We present a technique that allows overcoming these…

To solve Math Word Problems, human students leverage diverse reasoning logic that reaches different possible equation solutions. However, the mainstream sequence-to-sequence approach of automatic solvers aims to decode a fixed solution…

Effective code generation requires both model capability and a problem representation that carefully structures how models reason and plan. Existing approaches augment reasoning steps or inject specific structure into how models think, but…

With the rapid development of deep learning, most of current state-of-the-art techniques in natural langauge processing are based on deep learning models trained with argescaled static textual corpora. However, we human beings learn and…

Large Language Models (LLMs) have shown remarkable capabilities in manipulating natural language across multiple applications, but their ability to handle simple reasoning tasks is often questioned. In this work, we aim to provide a…

The recent trend towards utilisation of reasoning models has improved the performance of Large Language Models (LLMs) across many tasks which involve logical steps. One linguistic task that could benefit from this framing is idiomaticity…

Automating code documentation through explanatory text can prove highly beneficial in code understanding. Large Language Models (LLMs) have made remarkable strides in Natural Language Processing, especially within software engineering tasks…

We demonstrate experimental results with LLMs that address robotics task planning problems. Recently, LLMs have been applied in robotics task planning, particularly using a code generation approach that converts complex high-level…

Large language models (LLMs) can solve problems step-by-step. While this chain-of-thought (CoT) reasoning boosts LLMs' performance, it is unclear if LLMs \textit{know} when to use CoT and whether those CoT are always necessary to answer the…

Large language models (LLMs) exhibit strong reasoning abilities, often attributed to few-shot or zero-shot chain-of-thought (CoT) prompting. While effective, these methods require labor-intensive prompt engineering, raising the question of…

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…

Math is constructed by people for people: just as natural language corpora reflect not just propositions but the communicative goals of language users, the math data that models are trained on reflects not just idealized mathematical…

Vision-Language Models (VLMs) have recently gained attention due to their competitive performance on multiple downstream tasks, achieved by following user-input instructions. However, VLMs still exhibit several limitations in visual…

Logical reasoning is central to human cognition and intelligence. It includes deductive, inductive, and abductive reasoning. Past research of logical reasoning within AI uses formal language as knowledge representation and symbolic…

Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text. While the dominant recipe for conditional text generation has been large-scale pretrained language models…

Pretrained large language models (LLMs) are widely used in many sub-fields of natural language processing (NLP) and generally known as excellent few-shot learners with task-specific exemplars. Notably, chain of thought (CoT) prompting, a…

Iterative evaluation of LLMs during training is essential to ensure expected capability development, but can be time- and compute-intensive. While NLU tasks, where the model selects from fixed answer choices, are cheap to evaluate,…

Due to the remarkable language understanding and generation abilities of large language models (LLMs), their use in educational applications has been explored. However, little work has been done on investigating the pedagogical ability of…