English
Related papers

Related papers: Reasoning as an Adaptive Defense for Safety

200 papers

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In…

Computation and Language · Computer Science 2025-05-21 Jiaxin Guo , Zewen Chi , Li Dong , Qingxiu Dong , Xun Wu , Shaohan Huang , Furu Wei

Generating grounded and trustworthy responses remains a key challenge for large language models (LLMs). While retrieval-augmented generation (RAG) with citation-based grounding holds promise, instruction-tuned models frequently fail even in…

Computation and Language · Computer Science 2025-06-19 Shang Hong Sim , Tej Deep Pala , Vernon Toh , Hai Leong Chieu , Amir Zadeh , Chuan Li , Navonil Majumder , Soujanya Poria

Although preference optimization methods have improved reasoning performance in Large Language Models (LLMs), they often lack transparency regarding why one reasoning outcome is preferred over another. This limitation is especially critical…

Computation and Language · Computer Science 2025-09-30 Jiazheng Li , Yuxiang Zhou , Junru Lu , Gladys Tyen , Lin Gui , Cesare Aloisi , Yulan He

LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate reasoning steps, verifying their correctness, and selecting…

Large Audio Language Models (LALMs), powered by the chain-of-thought (CoT) paradigm, have shown remarkable reasoning capabilities. Intuitively, different problems often require varying depths of reasoning. While some methods can determine…

Machine Learning · Computer Science 2025-11-20 Zhichao Sheng , Shilin Zhou , Chen Gong , Zhenghua Li

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…

Cryptography and Security · Computer Science 2025-11-11 Haonan Shi , Guoli Wang , Tu Ouyang , An Wang

Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewards (RLVR) derives outcome signals from executable checks or…

Computation and Language · Computer Science 2026-05-25 Sirui Chen , Lei Xu , Yuying Zhao , Yutian Chen , Yu Wang , Beier Zhu , Hanwang Zhang , Shengjie Zhao , Chaochao Lu

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their explicit chain-of-thought (CoT) mechanism introduces new…

Artificial Intelligence · Computer Science 2026-05-26 Jianan Li , Simeng Qin , Xiaojun Jia , Lionel Z. Wang , Tianhang Zheng , Xiaoshuang Jia , Yang Liu , Xiaochun Cao

Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer). This weakness is even evident in temporal question answering, where models frequently…

Computation and Language · Computer Science 2026-03-05 Xinyu Zhou , Chang Jin , Carsten Eickhoff , Zhijiang Guo , Seyed Ali Bahrainian

Reinforcement learning exhibits potential in enhancing the reasoning abilities of large language models, yet it is hard to scale for the low sample efficiency during the rollout phase. Existing methods attempt to improve efficiency by…

Machine Learning · Computer Science 2026-02-02 Deyang Kong , Qi Guo , Xiangyu Xi , Wei Wang , Jingang Wang , Xunliang Cai , Shikun Zhang , Wei Ye

Large Reasoning Models (LRMs) often suffer from computational inefficiency due to overthinking, where a fixed reasoning budget fails to match the varying complexity of tasks. To address this issue, we propose Adaptive Overclocking, a method…

Machine Learning · Computer Science 2025-09-23 Shuhao Jiang , Songbo Wang , Yang Qiao , Chun Xu , Chaoyang Zheng , Shengyi Zhou , Huanjun Wang , Fangming Li , Cong Zhang , Jiyu Wang

Reasoning Language Models, capable of extended chain-of-thought reasoning, have demonstrated remarkable performance on tasks requiring complex logical inference. However, applying elaborate reasoning for all queries often results in…

Computation and Language · Computer Science 2025-06-27 Gongfan Fang , Xinyin Ma , Xinchao Wang

While Multimodal Large Language Models (MLLMs) have made remarkable progress in vision-language reasoning, they are also more susceptible to producing harmful content compared to models that focus solely on text. Existing defensive…

Computation and Language · Computer Science 2024-12-30 Yilei Jiang , Yingshui Tan , Xiangyu Yue

Large Language Models (LLMs), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporating external tools,…

Computation and Language · Computer Science 2025-07-30 Yifan Wei , Xiaoyan Yu , Yixuan Weng , Tengfei Pan , Angsheng Li , Li Du

Complex clinical decision making often fails not because a model lacks facts, but because it cannot reliably select and apply the right procedural knowledge and the right prior example at the right reasoning step. We frame clinical question…

Information Retrieval · Computer Science 2026-03-03 Junda Wang , Zonghai Tao , Hansi Zeng , Zhichao Yang , Hamed Zamani , Hong Yu

Red-teaming is a common practice for mitigating unsafe behaviors in Large Language Models (LLMs), which involves thoroughly assessing LLMs to identify potential flaws and addressing them with responsible and accurate responses. While…

Computation and Language · Computer Science 2023-11-15 Suyu Ge , Chunting Zhou , Rui Hou , Madian Khabsa , Yi-Chia Wang , Qifan Wang , Jiawei Han , Yuning Mao

Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In contrast, we propose a verifier-guided adaptive framework treating reasoning as iterative…

Computation and Language · Computer Science 2026-04-08 Ahsan Bilal , Ahmed Mohsin , Muhammad Umer , Ali Subhan , Hassan Rizwan , Ayesha Mohsin , Dean Hougen

Modern agents powered by thinking LLMs achieve high accuracy through long chain-of-thought reasoning but incur substantial inference costs. While many LLMs now support configurable reasoning levels (e.g., high/medium/low), static strategies…

Artificial Intelligence · Computer Science 2026-03-10 Jingbo Yang , Bairu Hou , Wei Wei , Yujia Bao , Shiyu Chang

Modern large language model (LLM) developers typically conduct a safety alignment to prevent an LLM from generating unethical or harmful content. Recent studies have discovered that the safety alignment of LLMs can be bypassed by…

Cryptography and Security · Computer Science 2024-06-14 Xuan Chen , Yuzhou Nie , Lu Yan , Yunshu Mao , Wenbo Guo , Xiangyu Zhang

Instruction tuning -- supervised fine-tuning using instruction-response pairs -- is a key step in making pre-trained large language models (LLMs) instructable. Meanwhile, LLMs perform multitask learning during their pre-training, acquiring…

Computation and Language · Computer Science 2025-09-16 Seokhyun An , Minji Kim , Hyounghun Kim