Related papers: Natural Language Proof Checking in Introduction to…
We present LISA, a proof system and proof assistant for constructing proofs in schematic first-order logic and axiomatic set theory. The logical kernel of the system is a proof checker for first-order logic with equality and schematic…
This paper documents our experience using declarative languages to give secondary school students a first taste of Computer Science. The course aims to teach students a bit about programming in Prolog, but also exposes them to important…
We propose utilizing background operators for mathematical reasoning in large language models (LLMs). To achieve this, we define a set of fundamental mathematical predicates as the basic building blocks. For each mathematical problem, we…
The goal of this thesis is to advance the exploration of the statistical language learning design space. In pursuit of that goal, the thesis makes two main theoretical contributions: (i) it identifies a new class of designs by specifying an…
The probing methodology allows one to obtain a partial representation of linguistic phenomena stored in the inner layers of the neural network, using external classifiers and statistical analysis. Pre-trained transformer-based language…
In this article, we use probing to investigate phenomena that occur during fine-tuning and knowledge distillation of a BERT-based natural language understanding (NLU) model. Our ultimate purpose was to use probing to better understand…
Background: In times when the ability to program is becoming increasingly important, it is still difficult to teach students to become successful programmers. One remarkable aspect are recent findings from neuro-imaging studies, which…
Large language models have achieved remarkable success on final-answer mathematical problems, largely due to the ease of applying reinforcement learning with verifiable rewards. However, the reasoning underlying these solutions is often…
Discrete prompts have been used for fine-tuning Pre-trained Language Models for diverse NLP tasks. In particular, automatic methods that generate discrete prompts from a small set of training instances have reported superior performance.…
In recent progress, mathematical verifiers have achieved success in mathematical reasoning tasks by validating the correctness of solutions generated by policy models. However, existing verifiers are trained with binary classification…
This work discusses an approach to teach to mathematicians the importance and effectiveness of the application of Interactive Theorem Proving tools in their specific fields of interest. The approach aims to motivate the use of such tools…
Proof search in non-confluent tableau calculi, such as the connection tableau calculus, suffers from excess backtracking, but simple restrictions on backtracking are incomplete. We adopt constraint learning to reduce backtracking in the…
Large language models (LLMs) benefit greatly from prompt engineering, with in-context learning standing as a pivital technique. While former approaches have provided various ways to construct the demonstrations used for in-context learning,…
Grammatical error correction systems improve written communication by detecting and correcting language mistakes. To help language learners better understand why the GEC system makes a certain correction, the causes of errors (evidence…
Providing natural language explanations for recommendations is particularly useful from the perspective of a non-expert user. Although several methods for providing such explanations have recently been proposed, we argue that an important…
Few-shot learning has drawn researchers' attention to overcome the problem of data scarcity. Recently, large pre-trained language models have shown great performance in few-shot learning for various downstream tasks, such as question…
Current methods for prompt learning in zeroshot scenarios widely rely on a development set with sufficient human-annotated data to select the best-performing prompt template a posteriori. This is not ideal because in a realworld zero-shot…
Our goal is to create a convenient natural language interface for performing well-specified but complex actions such as analyzing data, manipulating text, and querying databases. However, existing natural language interfaces for such tasks…
Accurate spelling correction is a critical step in modern search interfaces, especially in an era of mobile devices and speech-to-text interfaces. For services that are deployed around the world, this poses a significant challenge for…
We introduce a high-level language with Python-like syntax for string-to-string, polyregular, first-order definable transductions. This language features function calls, boolean variables, and nested for-loops. We devise and implement a…