9 papers
SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing
Aidan Wen, Norah A. Alzahrani, Jingzhi Jiang +5
We introduce SeedAIchemy, an automated LLM-driven corpus generation tool that makes it easier for developers to implement fuzzing effectively. SeedAIchemy consists of five modules…
Do Large Language Models Excel in Complex Logical Reasoning with Formal Language?
Jin Jiang, Jianing Wang, Yuchen Yan +5
Large Language Models (LLMs) have been shown to achieve breakthrough performance on complex logical reasoning tasks. Nevertheless, most existing research focuses on employing forma…
Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition
Yu Li, Jin Jiang, Jianhua Zhu +4
Handwritten Mathematical Expression Recognition (HMER) remains a persistent challenge in Optical Character Recognition (OCR) due to the inherent freedom of symbol layouts and varia…
VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
Yuchen Yan, Jin Jiang, Zhenbang Ren +9
Large reasoning models such as OpenAI o1 and DeepSeek-R1 have demonstrated remarkable performance in complex reasoning tasks. A critical component of their training is the incorpor…
Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning
Jianing Wang, Jin Jiang, Yang Liu +2
In this paper, we introduce a new \emph{process prejudge} strategy in LLM reasoning to demonstrate that bootstrapping with process prejudge allows the LLM to adaptively anticipate…
InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models
Yuchen Yan, Yongliang Shen, Yang Liu +4
Advanced reasoning in large language models has achieved remarkable performance on challenging tasks, but the prevailing long-context reasoning paradigm faces critical limitations:…
MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task
Yuchen Yan, Yongliang Shen, Yang Liu +5
Mathematical reasoning represents a critical frontier in advancing large language models (LLMs). While step-by-step approaches have emerged as the dominant paradigm for mathematica…
LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning
Jin Jiang, Yuchen Yan, Yang Liu +6
In this paper, we propose a new data synthesis method called \textbf{LogicPro}, which leverages LeetCode-style algorithm \underline{Pro}blems and their corresponding \underline{Pro…
S^3cMath: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners
Yuchen Yan, Jin Jiang, Yang Liu +5
Self-correction is a novel method that can stimulate the potential reasoning abilities of large language models (LLMs). It involves detecting and correcting errors during the infer…