中文
相关论文

相关论文: Evaluating the Safety and Skill Reasoning of Large…

200 篇论文

Recent advances in speech large language models (speech LLMs) have enabled seamless spoken interactions, but these systems still struggle with complex reasoning tasks. Previously, chain-of-thought (CoT) prompting or fine-tuning has been to…

计算与语言 · 计算机科学 2025-10-10 Yi-Jen Shih , Desh Raj , Chunyang Wu , Wei Zhou , SK Bong , Yashesh Gaur , Jay Mahadeokar , Ozlem Kalinli , Mike Seltzer

Reasoning-based language models have demonstrated strong performance across various domains, with the most notable gains seen in mathematical and coding tasks. Recent research has shown that reasoning also offers significant benefits for…

人工智能 · 计算机科学 2025-05-27 Makesh Narsimhan Sreedhar , Traian Rebedea , Christopher Parisien

Recent advances in test-time scaling suggest that Large Language Models (LLMs) can gain better capabilities by generating Chain-of-Thought reasoning (analogous to human thinking) to respond a given request, and meanwhile exploring more…

机器学习 · 计算机科学 2025-05-20 Yuhang Wang , Youhe Jiang , Bin Cui , Fangcheng Fu

Chain-of-Thought (CoT) reasoning enables Large Language Models (LLMs) to solve complex reasoning tasks by generating intermediate reasoning steps. However, most existing approaches focus on hard token decoding, which constrains reasoning…

计算与语言 · 计算机科学 2025-05-28 Yige Xu , Xu Guo , Zhiwei Zeng , Chunyan Miao

Large Audio-Language Models (LALMs) have demonstrated remarkable performance in tasks involving audio perception and understanding, such as speech recognition and audio captioning. However, their reasoning capabilities - critical for…

声音 · 计算机科学 2025-01-14 Ziyang Ma , Zhuo Chen , Yuping Wang , Eng Siong Chng , Xie Chen

Recent advances in natural language processing highlight two key factors for improving reasoning in large language models (LLMs): (i) allocating more test-time compute tends to help on harder problems but often introduces redundancy in the…

计算与语言 · 计算机科学 2025-11-04 Riccardo Alberghi , Elizaveta Demyanenko , Luca Biggio , Luca Saglietti

Sequential test-time scaling is a promising training-free method to improve large reasoning model accuracy, but as currently implemented, significant limitations have been observed. Inducing models to think for longer can increase their…

人工智能 · 计算机科学 2026-01-16 Michael R. Metel , Yufei Cui , Boxing Chen , Prasanna Parthasarathi

Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…

人工智能 · 计算机科学 2025-10-27 Ravindra Aribowo Tarunokusumo , Rafael Fernandes Cunha

Large reasoning models (LRMs) have exhibited remarkable reasoning capabilities through inference-time scaling, but this progress has also introduced considerable redundancy and inefficiency into their reasoning processes, resulting in…

人工智能 · 计算机科学 2025-07-18 Xingyang He , Xiao Ling , Jie Liu

Long chain-of-thought (CoT) is an essential ingredient in effective usage of modern large language models, but our understanding of the reasoning strategies underlying these capabilities remains limited. While some prior works have…

Long chains of thought (Long CoTs) are widely employed in multimodal reasoning models to tackle complex tasks by capturing detailed visual information. However, these Long CoTs are often excessively lengthy and contain redundant reasoning…

人工智能 · 计算机科学 2026-02-11 Yizhi Wang , Linan Yue , Min-Ling Zhang

We study a novel language model architecture that is capable of scaling test-time computation by implicitly reasoning in latent space. Our model works by iterating a recurrent block, thereby unrolling to arbitrary depth at test-time. This…

Recent advancements in slow thinking reasoning models have shown exceptional performance in complex reasoning tasks. However, these models often exhibit overthinking (generating redundant reasoning steps for simple problems), leading to…

机器学习 · 计算机科学 2026-01-13 Yi Shen , Jian Zhang , Jieyun Huang , Shuming Shi , Wenjing Zhang , Jiangze Yan , Ning Wang , Kai Wang , Zhaoxiang Liu , Shiguo Lian

Requiring a large language model (LLM) to generate intermediary reasoning steps, known as Chain of Thought (CoT), has been shown to be an effective way of boosting performance. Previous approaches have focused on generating multiple…

计算与语言 · 计算机科学 2025-05-28 Haritz Puerto , Tilek Chubakov , Xiaodan Zhu , Harish Tayyar Madabushi , Iryna Gurevych

Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining. Similarly, Chain-of-Thought (CoT)…

机器学习 · 计算机科学 2025-06-19 Baohao Liao , Hanze Dong , Yuhui Xu , Doyen Sahoo , Christof Monz , Junnan Li , Caiming Xiong

Long chain-of-thought (CoT) prompting helps Large Language Models (LLMs) solve difficult problems, but very long traces often slow or even degrade performance on fast, intuitive "System-1" tasks. We introduce Connector-Aware Compact CoT…

人工智能 · 计算机科学 2025-09-16 Sunguk Choi , Yonghoon Kwon , Heondeuk Lee

Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time as the length of the reasoning context increases. However,…

机器学习 · 计算机科学 2025-11-24 Chao Yu , Qixin Tan , Jiaxuan Gao , Shi Yu , Hong Lu , Xinting Yang , Zelai Xu , Yu Wang , Yi Wu , Eugene Vinitsky

Chain-of-thought prompting (CoT) has the potential to improve the explainability of language model reasoning. But CoT can also systematically misrepresent the factors influencing models' behavior -- for example, rationalizing answers in…

计算与语言 · 计算机科学 2025-06-30 James Chua , Edward Rees , Hunar Batra , Samuel R. Bowman , Julian Michael , Ethan Perez , Miles Turpin

Chain-of-Thought (CoT) prompting has significantly improved the reasoning capabilities of large language models (LLMs). However, conventional CoT often relies on unstructured, flat reasoning chains that suffer from redundancy and suboptimal…

计算与语言 · 计算机科学 2026-04-02 Xingshuai Huang , Derek Li , Bahareh Nikpour , Parsa Omidi

Chain-of-Thought (CoT) technique has proven effective in improving the performance of large language models (LLMs) on complex reasoning tasks. However, the performance gains are inconsistent across different tasks, and the underlying…

计算与语言 · 计算机科学 2025-06-09 Peijie Liu , Fengli Xu , Yong Li