相关论文: Training Verifiers to Solve Math Word Problems

Logical approaches to representing language have developed and evaluated computational models of quantifier words since the 19th century, but today's NLU models still struggle to capture their semantics. We rely on Generalized Quantifier…

Large language models show strong performance on knowledge intensive tasks such as fact-checking and question answering, yet they often struggle with numerical reasoning. We present a systematic evaluation of state-of-the-art models for…

Large language models (LLMs) are increasingly used to support the analysis of complex financial disclosures, yet their reliability, behavioral consistency, and transparency remain insufficiently understood in high-stakes settings. This…

Instruction tuning -- tuning large language models on instruction-output pairs -- is a promising technique for making models better adapted to the real world. Yet, the key factors driving the model's capability to understand and follow…

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

Large Language Models (LLMs) often struggle with tasks requiring mathematical reasoning, particularly multiple-choice questions (MCQs). To address this issue, we developed LLaMa-SciQ, an educational chatbot designed to assist college…

Common self-improvement approaches for large language models (LLMs), such as STaR, iteratively fine-tune LLMs on self-generated solutions to improve their problem-solving ability. However, these approaches discard the large amounts of…

Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges,…

The demonstrated code-understanding capability of LLMs raises the question of whether they can be used for automated program verification, a task that demands high-level abstract reasoning about program properties that is challenging for…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language and code generation, and are increasingly deployed as automatic judges of model outputs and learning activities. Yet, their behavior on structured…

As the field of Multimodal Large Language Models (MLLMs) continues to evolve, their potential to revolutionize artificial intelligence is particularly promising, especially in addressing mathematical reasoning tasks. Current mathematical…

We explored the challenges practitioners face in software testing and proposed automated solutions to address these obstacles. We began with a survey of local software companies and 26 practitioners, revealing that the primary challenge is…

We propose a novel system, MathMistake Checker, designed to automate step-by-step mistake finding in mathematical problems with lengthy answers through a two-stage process. The system aims to simplify grading, increase efficiency, and…

Reinforcement Learning with Verifiable Rewards (RLVR) has become a prominent method for post-training Large Language Models (LLMs). However, verifiers are rarely error-free; even deterministic checks can be inaccurate, and the growing…

Grammatical error correction (GEC) is the task of detecting and correcting grammatical errors in texts written by second language learners. The statistical machine translation (SMT) approach to GEC, in which sentences written by second…

As language models regularly make mistakes when solving math problems, automated identification of errors in the reasoning process becomes increasingly significant for their scalable oversight. In this paper, we introduce ProcessBench for…

Hallucinations in large language models (LLMs) have recently become a significant problem. A recent effort in this direction is a shared task at Semeval 2024 Task 6, SHROOM, a Shared-task on Hallucinations and Related Observable…

Large language models (LLMs) have achieved remarkable success in natural language processing (NLP), demonstrating significant capabilities in processing and understanding text data. However, recent studies have identified limitations in…

Large Language Models (LLMs) show promise for automated grading, but their outputs can be unreliable. Rather than improving grading accuracy directly, we address a complementary problem: \textit{predicting when an LLM grader is likely to be…

This study investigates the reasoning robustness of large language models (LLMs) on mathematical problem-solving tasks under systematically introduced input perturbations. Using the GSM8K dataset as a controlled testbed, we evaluate how…