中文
相关论文

相关论文: Asking the Right Questions: Improving Reasoning wi…

200 篇论文

Recent supervised fine-tuning (SFT) approaches have significantly improved language models' performance on mathematical reasoning tasks, even when models are trained at a small scale. However, the specific capabilities enhanced through such…

人工智能 · 计算机科学 2026-01-12 Yiyou Sun , Georgia Zhou , Haoyue Bai , Hao Wang , Dacheng Li , Nouha Dziri , Dawn Song

Large Language Models possess skills such as answering questions, writing essays or solving programming exercises. Since these models are easily accessible, researchers have investigated their capabilities and risks for programming…

计算机与社会 · 计算机科学 2023-12-19 Lianne Roest , Hieke Keuning , Johan Jeuring

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

机器学习 · 计算机科学 2025-10-28 Amal Abed , Ivan Lukic , Jörg K. H. Franke , Frank Hutter

Recent advances in large language models (LLMs) have significantly improved the performance of dialog systems, yet current approaches often fail to provide accurate guidance of topic due to their inability to discern user confusion in…

计算与语言 · 计算机科学 2025-08-20 Qi Wu , Zhongqi Lu

The context window of large language models (LLMs) has been extended significantly in recent years. However, while the context length that the LLM can process has grown, the capability of the model to accurately reason over that context…

计算与语言 · 计算机科学 2024-10-07 Huayang Li , Pat Verga , Priyanka Sen , Bowen Yang , Vijay Viswanathan , Patrick Lewis , Taro Watanabe , Yixuan Su

Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…

信息检索 · 计算机科学 2024-08-15 Jinxu Zhang

Multi-step reasoning instruction, such as chain-of-thought prompting, is widely adopted to explore better language models (LMs) performance. We report on the systematic strategy that LMs employ in such a multi-step reasoning process. Our…

计算与语言 · 计算机科学 2024-10-08 Yoichi Aoki , Keito Kudo , Tatsuki Kuribayashi , Shusaku Sone , Masaya Taniguchi , Keisuke Sakaguchi , Kentaro Inui

Mathematical reasoning is regarded as a necessary ability for Language Models (LMs). Recent works demonstrate large LMs' impressive performance in solving math problems. The success is attributed to their Chain-of-Thought (CoT) reasoning…

计算与语言 · 计算机科学 2023-06-08 Tianduo Wang , Wei Lu

When performing complex multi-step reasoning tasks, the ability of Large Language Models (LLMs) to derive structured intermediate proof steps is important for ensuring that the models truly perform the desired reasoning and for improving…

计算与语言 · 计算机科学 2025-01-31 Zi'ou Zheng , Christopher Malon , Martin Renqiang Min , Xiaodan Zhu

Large language models (LLMs) solve reasoning problems by first generating a rationale and then answering. We formalize reasoning as a latent variable model and derive a reward-based filtered expectation-maximization (FEM) objective for…

机器学习 · 计算机科学 2026-02-03 Junghyun Lee , Branislav Kveton , Anup Rao , Subhojyoti Mukherjee , Ryan A. Rossi , Sunav Choudhary , Alexa Siu

Reasoning plays a crucial role in advancing Multimodal Large Language Models (MLLMs) toward Artificial General Intelligence. However, existing MLLM benchmarks often fall short in precisely and comprehensively evaluating long-chain reasoning…

As language model (LM) outputs get more and more natural, it is becoming more difficult than ever to evaluate their quality. Simultaneously, increasing LMs' "thinking" time through scaling test-time compute has proven an effective technique…

Entity matching is a fundamental task in data cleaning and data integration. With the rapid adoption of large language models (LLMs), recent studies have explored zero-shot and few-shot prompting to improve entity matching accuracy.…

数据库 · 计算机科学 2025-12-01 Rohan Bopardikar , Jin Wang , Jia Zou

Logical reasoning is a pivotal component in the field of artificial intelligence. Proof planning, particularly in contexts requiring the validation of explanation accuracy, continues to present challenges. The recent advancement of large…

计算与语言 · 计算机科学 2025-10-31 Ying Su , Mingwen Liu , Zhijiang Guo

Large language model (LLM) driven synthetic data generation has emerged as a powerful method for improving model reasoning capabilities. However, most methods either distill large state-of-the-art models into small students or use natural…

机器学习 · 计算机科学 2025-06-18 Alex Havrilla , Edward Hughes , Mikayel Samvelyan , Jacob Abernethy

Although LLMs have shown great performance on Mathematics and Coding related reasoning tasks, the reasoning capabilities of LLMs regarding other forms of reasoning are still an open problem. Here, we examine the issue of reasoning from the…

计算与语言 · 计算机科学 2025-06-18 John Dougrez-Lewis , Mahmud Elahi Akhter , Federico Ruggeri , Sebastian Löbbers , Yulan He , Maria Liakata

We explore the use of small language models (SLMs) for automatic question generation as a complement to the prevalent use of their large counterparts in learning analytics research. We present a novel question generation pipeline that…

计算与语言 · 计算机科学 2026-01-19 Yumou Wei , John Stamper , Paulo F. Carvalho

Mathematical reasoning has been challenging for large language models (LLMs), and the introduction of step-by-step Chain-of-Thought (CoT) inference has significantly advanced the mathematical capabilities of LLMs. However, current…

人工智能 · 计算机科学 2025-09-23 Lang Cao , Yingtian Zou , Chao Peng , Renhong Chen , Wu Ning , Yitong Li

This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. The former is defined as decomposing a potentially complex task into simpler subtasks while the latter consists in…

Step-by-step reasoning has become a standard approach for large language models (LLMs) to tackle complex tasks. While this paradigm has proven effective, it raises a fundamental question: How can we verify that an LLM's reasoning is…

计算与语言 · 计算机科学 2025-11-04 Hyeon Hwang , Yewon Cho , Chanwoong Yoon , Yein Park , Minju Song , Kyungjae Lee , Gangwoo Kim , Jaewoo Kang