相关论文: Math Word Problem Solving by Generating Linguistic…

Large language models (LLMs) have demonstrated strong performance on coding tasks such as generation, completion and repair, but their ability to handle complex symbolic reasoning over code still remains underexplored. We introduce the task…

More recently, Bidirectional Encoder Representations from Transformers (BERT) was proposed and has achieved impressive success on many natural language processing (NLP) tasks such as question answering and language understanding, due mainly…

Theorem proving in natural mathematical language - the mixture of symbolic and natural language used by humans - plays a central role in mathematical advances and education, and tests aspects of reasoning that are core to intelligence. Yet…

Mainstream Word Sense Disambiguation (WSD) approaches have employed BERT to extract semantics from both context and definitions of senses to determine the most suitable sense of a target word, achieving notable performance. However, there…

The paper presents an experiment of solving word equations via specialization of a configuration WE(R,E), where the program WE can be considered as an interpreter testing whether a composition of substitutions R produces a solution of a…

The mathematical representation of semantics is a key issue for Natural Language Processing (NLP). A lot of research has been devoted to finding ways of representing the semantics of individual words in vector spaces. Distributional…

Neural machine translation (NMT), a new approach to machine translation, has achieved promising results comparable to those of traditional approaches such as statistical machine translation (SMT). Despite its recent success, NMT cannot…

The objective of this study is to improve automated feedback tools designed for English Language Learners (ELLs) through the utilization of data science techniques encompassing machine learning, natural language processing, and educational…

Current frameworks for consensus statement generation with large language models lack the inherent structure needed to provide provable fairness guarantees when aggregating diverse free-form opinions. We model the task as a multi-objective,…

Multilingual understanding models (or encoder-based), pre-trained via masked language modeling, have achieved promising results on many language understanding tasks (e.g., mBERT). However, these non-autoregressive (NAR) models still…

Mathematical reasoning and optimization are fundamental to artificial intelligence and computational problem-solving. Recent advancements in Large Language Models (LLMs) have significantly improved AI-driven mathematical reasoning, theorem…

Bit-vector formulas arising from hardware verification problems often contain word-level arithmetic operations. Empirical evidence shows that state-of-the-art SMT solvers are not very efficient at reasoning about bit-vector formulas with…

Despite the advancements in large language models (LLMs) for mathematical reasoning, solving competition-level math problems remains a significant challenge, especially for open-source LLMs without external tools. We introduce the MMIQC…

Large Language Models (LLMs) have shown remarkable success on a wide range of math and reasoning benchmarks. However, we observe that they often struggle when faced with unreasonable math problems. Instead of recognizing these issues,…

Traditional sentence embedding methods employ token-level contrastive learning on non-generative pre-trained models. Recently, there have emerged embedding methods based on generative large language models (LLMs). These methods either rely…

We introduce Meta-Reasoning Prompting (MRP), a novel and efficient system prompting method for large language models (LLMs) inspired by human meta-reasoning. Traditional in-context learning-based reasoning techniques, such as…

The advent of large reasoning models, such as OpenAI o1 and DeepSeek R1, has significantly advanced complex reasoning tasks. However, their capabilities in multilingual complex reasoning remain underexplored, with existing efforts largely…

As LLMs reduce English-centric bias, a surprising trend emerges: non-English responses sometimes outperform English on reasoning tasks. We hypothesize that language functions as a latent variable that structurally modulates the model's…

Estimating the difficulty level of math word problems is an important task for many educational applications. Identification of relevant and irrelevant sentences in math word problems is an important step for calculating the difficulty…

Multiple-choice questions (MCQs) are commonly used across all levels of math education since they can be deployed and graded at a large scale. A critical component of MCQs is the distractors, i.e., incorrect answers crafted to reflect…