English
Related papers

Related papers: MENTOR: A Metacognition-Driven Self-Evolution Fram…

200 papers

Human guidance in reinforcement learning (RL) is often impractical for large-scale applications due to high costs and time constraints. Large Language Models (LLMs) offer a promising alternative to mitigate RL sample inefficiency and…

Machine Learning · Computer Science 2024-11-25 Maryam Shoaeinaeini , Brent Harrison

Reflection, the ability of large language models (LLMs) to evaluate and revise their own reasoning, has been widely used to improve performance on complex reasoning tasks. Yet, most prior works emphasizes designing reflective prompting…

Machine Learning · Computer Science 2025-12-12 Fu-Chieh Chang , Yu-Ting Lee , Pei-Yuan Wu

Large language models (LLMs) are now ubiquitous in everyday tools, raising urgent safety concerns about their tendency to generate harmful content. The dominant safety approach -- reinforcement learning from human feedback (RLHF) --…

Machine Learning · Computer Science 2025-09-29 Sathwik Karnik , Somil Bansal

Large Language Models (LLMs) often struggle with computational efficiency and error propagation in multi-step reasoning tasks. While recent advancements on prompting and post-training have enabled LLMs to perform step-wise reasoning, they…

Artificial Intelligence · Computer Science 2026-05-08 Yuan Sui , Yufei He , Tri Cao , Simeng Han , Yulin Chen , Bryan Hooi

Ensuring LLM alignment is critical to information security as AI models become increasingly widespread and integrated in society. Unfortunately, many defenses against adversarial attacks and jailbreaking on LLMs cannot adapt quickly to new…

Cryptography and Security · Computer Science 2025-08-12 Ivan Zhang

Large language models (LLMs) are prone to hallucination stemming from misaligned self-awareness, particularly when processing queries exceeding their knowledge boundaries. While existing mitigation strategies employ uncertainty estimation…

Computation and Language · Computer Science 2025-10-10 Hang Zheng , Hongshen Xu , Yuncong Liu , Lu Chen , Pascale Fung , Kai Yu

Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores…

Cryptography and Security · Computer Science 2026-01-06 Jirui Yang , Zheyu Lin , Zhihui Lu , Yinggui Wang , Lei Wang , Tao Wei , Qiang Duan , Xin Du , Shuhan Yang

We propose a novel dynamic safety framework that optimizes language model (LM) safety reasoning at inference time without modifying model weights. Building on recent advances in self-critique methods, our approach leverages a meta-critique…

Computation and Language · Computer Science 2025-04-08 Víctor Gallego

Large Language Models (LLMs) have developed rapidly in web services, delivering unprecedented capabilities while amplifying societal risks. Existing works tend to focus on either isolated jailbreak attacks or static defenses, neglecting the…

Cryptography and Security · Computer Science 2025-11-27 Xurui Li , Kaisong Song , Rui Zhu , Pin-Yu Chen , Haixu Tang

This study reveals a critical safety blind spot in modern LLMs: learning-style queries, which closely resemble ordinary educational questions, can reliably elicit harmful responses. The learning-style queries are constructed by a novel…

Cryptography and Security · Computer Science 2026-02-25 Xuan Luo , Yue Wang , Zefeng He , Geng Tu , Jing Li , Ruifeng Xu

Autonomous agents based on Large Language Models (LLMs) are increasingly being utilized in complex software systems. However, reliability remains a significant challenge due to unpredictable failures such as hallucinations, execution…

Software Engineering · Computer Science 2026-05-11 Cheonsu Jeong , Younggun Shin

Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art models. Existing alignment-based and guardrail methods…

Cryptography and Security · Computer Science 2026-04-21 Bo Yan , Weikai Lin , Yada Zhu , Song Wang

The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks,…

Cryptography and Security · Computer Science 2024-10-01 Qin Liu , Wenjie Mo , Terry Tong , Jiashu Xu , Fei Wang , Chaowei Xiao , Muhao Chen

As large language models (LLMs) grow in power and influence, ensuring their safety and preventing harmful output becomes critical. Automated red teaming serves as a tool to detect security vulnerabilities in LLMs without manual labor.…

Artificial Intelligence · Computer Science 2025-06-03 Weiyang Guo , Zesheng Shi , Zhuo Li , Yequan Wang , Xuebo Liu , Wenya Wang , Fangming Liu , Min Zhang , Jing Li

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Machine Learning · Computer Science 2025-05-22 Tong Wu , Chong Xiang , Jiachen T. Wang , G. Edward Suh , Prateek Mittal

Privacy-preserving adaptation of Large Language Models (LLMs) in sensitive domains (e.g., mental health) requires balancing strict confidentiality with model utility and safety. We propose FedMentor, a federated fine-tuning framework that…

Cryptography and Security · Computer Science 2026-01-27 Nobin Sarwar , Shubhashis Roy Dipta

Current studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks. However, they overlook that the direct generation of harmful content from scratch is more difficult than inducing LLM to…

Computation and Language · Computer Science 2026-02-12 Yu Yan , Sheng Sun , Zenghao Duan , Teli Liu , Min Liu , Zhiyi Yin , Jingyu Lei , Qi Li

While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment paradigms primarily rely on externally enforced compliance, optimizing models to detect…

Artificial Intelligence · Computer Science 2026-05-12 Yi Zhang , Yuxin Chen , Leheng Sheng , Dongcheng Zhang , Chaochao Lu , Xiang Wang , An Zhang

Reinforcement learning (RL) has enabled the training of large language model (LLM) agents to interact with the environment and to solve multi-turn long-horizon tasks. However, the RL-trained agents often struggle in tasks that require…

Machine Learning · Computer Science 2026-03-10 Yulun Jiang , Liangze Jiang , Damien Teney , Michael Moor , Maria Brbic

Strategic planning is critical for multi-step reasoning, yet compact Large Language Models (LLMs) often lack the capacity to formulate global strategies, leading to error propagation in long-horizon tasks. Our analysis reveals that LLMs…

Computation and Language · Computer Science 2026-04-15 Haoyu Zheng , Yun Zhu , Yuqian Yuan , Bo Yuan , Wenqiao Zhang , Siliang Tang , Jun Xiao