中文
相关论文

相关论文: Unleashing Scientific Reasoning for Bio-experiment…

200 篇论文

The sheer volume of scientific experimental results and complex technical statements, often presented in tabular formats, presents a formidable barrier to individuals acquiring preferred information. The realms of scientific reasoning and…

计算与语言 · 计算机科学 2024-03-28 Zhixin Guo , Jianping Zhou , Jiexing Qi , Mingxuan Yan , Ziwei He , Guanjie Zheng , Zhouhan Lin , Xinbing Wang , Chenghu Zhou

Although Large Language Models (LLMs) excel at addressing straightforward reasoning tasks, they frequently struggle with difficulties when confronted by more complex multi-step reasoning due to a range of factors. Firstly, natural language…

计算与语言 · 计算机科学 2024-02-22 Kewei Cheng , Nesreen K. Ahmed , Theodore Willke , Yizhou Sun

Multi-hop Question Generation is the task of generating questions which require the reader to reason over and combine information spread across multiple passages using several reasoning steps. Chain-of-thought rationale generation has been…

计算与语言 · 计算机科学 2022-11-17 Saurabh Kulshreshtha , Anna Rumshisky

Interactive medical questioning is essential in real-world clinical consultations, where physicians must actively gather information from patients. While medical Large Language Models (LLMs) have shown impressive capabilities in static…

计算与语言 · 计算机科学 2025-08-20 Hongxin Ding , Baixiang Huang , Yue Fang , Weibin Liao , Xinke Jiang , Zheng Li , Junfeng Zhao , Yasha Wang

Long-horizon precision manipulation in laboratory automation, such as pipette tip attachment and liquid transfer, requires policies that respect strict procedural logic while operating in continuous, high-dimensional state spaces. However,…

机器人学 · 计算机科学 2026-03-03 Yibo Qiu , Shu'ang Sun , Haoliang Ye , Ronald X Xu , Mingzhai Sun

Large Language Models (LLMs) excel in complex reasoning tasks but struggle with consistent rule application, exception handling, and explainability, particularly in domains like legal analysis that require both natural language…

人工智能 · 计算机科学 2025-11-11 Albert Sadowski , Jarosław A. Chudziak

Training on verifiable symbolic data is a promising way to expand the reasoning frontier of language models beyond what standard pre-training corpora provide. Yet existing procedural generators often rely on fixed puzzles or templates and…

计算与语言 · 计算机科学 2026-03-03 Valentin Lacombe , Valentin Quesnel , Damien Sileo

Existing Vision-Language Models often struggle with complex, multi-question reasoning tasks where partial correctness is crucial for effective learning. Traditional reward mechanisms, which provide a single binary score for an entire…

Scientific literature is growing exponentially, creating a critical bottleneck for researchers to efficiently synthesize knowledge. While general-purpose Large Language Models (LLMs) show potential in text processing, they often fail to…

计算与语言 · 计算机科学 2025-09-11 Fengyu She , Nan Wang , Hongfei Wu , Ziyi Wan , Jingmian Wang , Chang Wang

LLM-driven program evolution has emerged as a powerful tool for automated scientific discovery, yet existing frameworks offer no principled guide for designing their individual components and provide no guarantee that the search converges.…

人工智能 · 计算机科学 2026-05-18 Jiachen Jiang , Huminhao Zhu , Zhihui Zhu

Recent advancements in large language models (LLMs) underscore the need for stronger reasoning capabilities to solve complex problems effectively. While Chain-of-Thought (CoT) reasoning has been a step forward, it remains insufficient for…

计算与语言 · 计算机科学 2025-07-14 Matan Vetzler , Koren Lazar , Guy Uziel , Eran Hirsch , Ateret Anaby-Tavor , Leshem Choshen

Recent advances in large language models (LLMs) have enabled strong reasoning capabilities through Chain-of-Thought (CoT) prompting, which elicits step-by-step problem solving, but often at the cost of excessive verbosity in intermediate…

计算与语言 · 计算机科学 2025-10-27 Simon A. Aytes , Jinheon Baek , Sung Ju Hwang

In this paper, we study how to improve the zero-shot reasoning ability of large language models~(LLMs) over structured data in a unified way. Inspired by the study on tool augmentation for LLMs, we develop an \emph{Iterative…

计算与语言 · 计算机科学 2023-10-24 Jinhao Jiang , Kun Zhou , Zican Dong , Keming Ye , Wayne Xin Zhao , Ji-Rong Wen

This paper explores a top-down approach to automating incremental advances in machine learning research through component-level innovation, facilitated by Large Language Models (LLMs). Our framework systematically generates novel…

机器学习 · 计算机科学 2024-09-10 Shervin Ardeshir

A rational design of new therapeutic drugs aims to find a molecular structure with desired biological functionality, e.g., an ability to activate or suppress a specific protein via binding to it. Molecular docking is a common technique for…

Signal Temporal Logic (STL) is a powerful formal language for specifying real-time specifications of Cyber-Physical Systems (CPS). Transforming specifications written in natural language into STL formulas automatically has attracted…

形式语言与自动机理论 · 计算机科学 2025-11-12 Yue Fang , Jin Zhi , Jie An , Hongshen Chen , Xiaohong Chen , Naijun Zhan

Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs). The previous studies have elucidated the merits of integrating feedback or search mechanisms during model inference to improve the…

计算与语言 · 计算机科学 2023-10-17 Qianli Ma , Haotian Zhou , Tingkai Liu , Jianbo Yuan , Pengfei Liu , Yang You , Hongxia Yang

Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward models to produce explicit, multi-dimensional critiques…

人工智能 · 计算机科学 2026-04-15 Haozhe Wang , Cong Wei , Weiming Ren , Jiaming Liu , Fangzhen Lin , Wenhu Chen

Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and problem-solving across various domains. However, their ability to perform complex, multi-step reasoning task-essential…

Tool invocation significantly enhances the capabilities of Large Language Models (LLMs), yet challenges persist, particularly in complex task scenarios. Current methods, such as instruction-enhanced reasoning and supervised fine-tuning,…

人工智能 · 计算机科学 2025-08-07 Yifei Lu , Fanghua Ye , Jian Li , Qiang Gao , Cheng Liu , Haibo Luo , Nan Du , Xiaolong Li , Feiliang Ren