English
Related papers

Related papers: Crystal: Introspective Reasoners Reinforced with S…

200 papers

The dominant paradigm for training large reasoning models starts with pre-training using next-token prediction loss on vast amounts of data. Reinforcement learning, while powerful in scaling reasoning, is introduced only as the very last…

The internalization of chain-of-thought processes into hidden states has emerged as a highly efficient paradigm for scaling test-time compute. However, existing activation steering methods rely on static control vectors that fail to adapt…

Machine Learning · Computer Science 2026-02-06 Zhenning Shi , Yijia Zhu , Junhan Shi , Xun Zhang , Lei Wang , Congcong Miao

Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial…

Recently, end-to-end trained models for multiple-choice commonsense question answering (QA) have delivered promising results. However, such question-answering systems cannot be directly applied in real-world scenarios where answer…

Computation and Language · Computer Science 2023-03-21 Zhen Han , Yue Feng , Mingming Sun

Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations…

Computation and Language · Computer Science 2024-11-27 Tim Hartill

Selective rationalization has become a common mechanism to ensure that predictive models reveal how they use any available features. The selection may be soft or hard, and identifies a subset of input features relevant for prediction. The…

Computation and Language · Computer Science 2019-12-17 Mo Yu , Shiyu Chang , Yang Zhang , Tommi S. Jaakkola

In the absence of extensive human-annotated data for complex reasoning tasks, self-improvement -- where models are trained on their own outputs -- has emerged as a primary method for enhancing performance. However, the critical factors…

Artificial Intelligence · Computer Science 2025-03-05 Weihao Zeng , Yuzhen Huang , Lulu Zhao , Yijun Wang , Zifei Shan , Junxian He

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale…

Computation and Language · Computer Science 2024-05-28 Kaituo Feng , Changsheng Li , Xiaolu Zhang , Jun Zhou , Ye Yuan , Guoren Wang

Large reasoning models (LRMs) exhibit unprecedented capabilities in solving complex problems through Chain-of-Thought (CoT) reasoning. However, recent studies reveal that their final answers often contradict their own reasoning traces. We…

Artificial Intelligence · Computer Science 2026-03-03 Yuhui Wang , Changjiang Li , Guangke Chen , Jiacheng Liang , Ting Wang

Recent advances in multimodal Reward Models (RMs) have shown significant promise in delivering reward signals to align vision models with human preferences. However, current RMs are generally restricted to providing direct responses or…

Computer Vision and Pattern Recognition · Computer Science 2025-10-30 Yibin Wang , Zhimin Li , Yuhang Zang , Chunyu Wang , Qinglin Lu , Cheng Jin , Jiaqi Wang

Large language models (LLMs) have shown impressive capabilities in handling complex tasks through long-chain reasoning. However, the extensive reasoning steps involved can significantly increase computational costs, posing challenges for…

Computation and Language · Computer Science 2025-05-28 Yunhao Wang , Yuhao Zhang , Tinghao Yu , Can Xu , Feng Zhang , Fengzong Lian

Traditional retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity within an embedding space. While efficient and scalable, this approach often fails to handle…

Computation and Language · Computer Science 2025-03-25 Felix Faltings , Wei Wei , Yujia Bao

It has been demonstrated that carefully designed reasoning paradigms, like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), can enhance the reasoning capabilities of small language models by detailed thinking and extensive thought…

Artificial Intelligence · Computer Science 2025-06-05 Yinlong Xu , Yanzhao Zheng , Shuoshuo Sun , Shuaihan Huang , Baohua Dong , Hangcheng Zhu , Ruohui Huang , Gang Yu , Hongxia Xu , Jian Wu

While deep reasoning with long chain-of-thought has dramatically improved large language models in verifiable domains like mathematics, its effectiveness for open-ended tasks such as writing remains unexplored. In this paper, we conduct a…

Computation and Language · Computer Science 2026-04-06 Wanlong Liu , Bo Zhang , Chenliang Li , Shaopeng Lai , Yuning Wu , Xuanyu Lei , Ming Yan

Test-time adaptation offers a promising avenue for improving reasoning performance in large language models without additional supervision, but existing approaches often apply a uniform optimization objective across all inputs, leading to…

Computation and Language · Computer Science 2026-03-06 Mohammad Mahdi Moradi , Sudhir Mudur

With software systems becoming increasingly pervasive and autonomous, our ability to test for their quality is severely challenged. Many systems are called to operate in uncertain and highly-changing environment, not rarely required to make…

Software Engineering · Computer Science 2024-03-21 Luca Giamattei , Roberto Pietrantuono , Stefano Russo

The role of reasoning in Audio Large Language Models remains widely underexplored, as introducing a reasoning process often degrades rather than improves performance during inference, a phenomenon we term test-time inverse scaling, where…

Machine Learning · Computer Science 2025-10-27 Jiajun Fan , Roger Ren , Jingyuan Li , Rahul Pandey , Prashanth Gurunath Shivakumar , Ivan Bulyko , Ankur Gandhe , Ge Liu , Yile Gu

Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-training share the core objective: iteratively leveraging…

Computation and Language · Computer Science 2025-05-27 Zongqian Wu , Baoduo Xu , Ruochen Cui , Mengmeng Zhan , Xiaofeng Zhu , Lei Feng

Rubrics have been extensively utilized for evaluating unverifiable, open-ended tasks, with recent research incorporating them into reward systems for reinforcement learning. However, existing frameworks typically treat rubrics only as…

Computation and Language · Computer Science 2026-05-11 Jiachen Yu , Zhihao Xu , Junjie Wang , Yujiu Yang

Large Language Models (LLMs) have shown strong reasoning capabilities, particularly when enhanced through Reinforcement Learning (RL). While prior work has successfully applied RL to mathematical reasoning -- where rules and correctness are…

‹ Prev 1 4 5 6 7 8 10 Next ›