English
Related papers

Related papers: The Compliance Paradox: Semantic-Instruction Decou…

200 papers

True self-evolution requires agents to act as lifelong learners that internalize novel experiences to solve future problems. However, rigorously measuring this foundational capability is hindered by two obstacles: the entanglement of prior…

Computation and Language · Computer Science 2026-05-12 Jiarui Yuan , Tailin Jin , Weize Chen , Zeyuan Liu

While Large Language Models (LLMs) have demonstrated exceptional proficiency in code completion, they typically adhere to a Hard Completion (HC) paradigm, compelling the generation of fully concrete code even amidst insufficient context.…

Computation and Language · Computer Science 2026-04-03 Liang Zhu , Haolin Chen , Lidong Zhao , Xian Wu

Inductive program synthesis, or programming by example, requires synthesizing functions from input-output examples that generalize to unseen inputs. While large language model agents have shown promise in programming tasks guided by natural…

Programming Languages · Computer Science 2025-08-11 Anjiang Wei , Tarun Suresh , Jiannan Cao , Naveen Kannan , Yuheng Wu , Kai Yan , Thiago S. F. X. Teixeira , Ke Wang , Alex Aiken

The widespread adoption of AI-assisted development tools in 2025 -- and the emergence of vibe coding, a practice of generating complete applications from natural language without verification -- exposed a critical and tool-agnostic failure…

Software Engineering · Computer Science 2026-05-01 Jasmine Moreira

Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities.…

Machine Learning · Computer Science 2026-01-06 Muxi Diao , Lele Yang , Wuxuan Gong , Yutong Zhang , Zhonghao Yan , Yufei Han , Kongming Liang , Weiran Xu , Zhanyu Ma

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…

Artificial Intelligence · Computer Science 2026-02-17 Igor Santos-Grueiro

Can a model learn to escape its own learning plateau? Reinforcement learning methods for finetuning large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental…

Machine Learning · Computer Science 2026-02-09 Shobhita Sundaram , John Quan , Ariel Kwiatkowski , Kartik Ahuja , Yann Ollivier , Julia Kempe

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire…

Cryptography and Security · Computer Science 2024-11-13 Xirui Li , Ruochen Wang , Minhao Cheng , Tianyi Zhou , Cho-Jui Hsieh

Despite the remarkable capabilities of large language models, current training paradigms inadvertently foster \textit{sycophancy}, i.e., the tendency of a model to agree with or reinforce user-provided information even when it's factually…

Artificial Intelligence · Computer Science 2025-09-23 Mohammad Beigi , Ying Shen , Parshin Shojaee , Qifan Wang , Zichao Wang , Chandan Reddy , Ming Jin , Lifu Huang

Large language models (LLMs) can fluently generate student-like responses, making them attractive as simulated students for training and evaluating AI tutors and human educators. Yet such simulators are typically evaluated by output…

Computation and Language · Computer Science 2026-05-14 Heejin Do , Shashank Sonkar , Mrinmaya Sachan

Adversarial robustness evaluation underpins every claim of trustworthy ML deployment, yet the field suffers from fragmented protocols and undetected gradient masking. We make two contributions. (1) Structured synthesis. We analyze nine…

Cryptography and Security · Computer Science 2026-04-23 Abhijit Talluri

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Haoyu Wang , Haonan Wang , Yuyan Chen , Jun Chen , Gang Liu , Qian Wang , Jiahong Yan , Yanghua Xiao

LLM-based software engineering assistants fail not only by producing incorrect outputs, but also by allocating trust to the wrong artifact when code, documentation, and tests disagree. Existing evaluations focus mainly on downstream…

Software Engineering · Computer Science 2026-04-07 Noshin Ulfat , Ahsanul Ameen Sabit , Soneya Binta Hossain

Alignment with high-resource standard languages is often assumed to aid the modeling of related low-resource varieties. We challenge this assumption by demonstrating that excessive representational entanglement with a dominant variety, such…

Computation and Language · Computer Science 2025-08-19 Ahmed Elshabrawy , Hour Kaing , Haiyue Song , Alham Fikri Aji , Hideki Tanaka , Masao Utiyama , Raj Dabre

Large Language Models (LLMs) exhibit impressive performance across various domains but still struggle with arithmetic reasoning tasks. Recent work shows the effectiveness of prompt design methods in enhancing reasoning capabilities.…

Computation and Language · Computer Science 2024-10-11 Wenting Tan , Dongxiao Chen , Jieting Xue , Zihao Wang , Taijie Chen

The application of large language models to code generation has evolved from one-shot generation to iterative refinement, yet the evolution of security throughout iteration remains insufficiently understood. Through comparative experiments…

Cryptography and Security · Computer Science 2026-03-10 Yi Chen , Yun Bian , Haiquan Wang , Shihao Li , Zhe Cui

Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to different prompt-based attacks, generating harmful content or sensitive information. Both closed-source and open-source LLMs are underinvestigated for these…

Cryptography and Security · Computer Science 2025-05-21 Jiawen Wang , Pritha Gupta , Ivan Habernal , Eyke Hüllermeier

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints (banning a single punctuation character or common word)…

Computation and Language · Computer Science 2026-04-28 Erfan Baghaei Potraghloo , Seyedarmin Azizi , Souvik Kundu , Massoud Pedram

Large Language Models (LLMs) are aligned to meet ethical standards and safety requirements by training them to refuse answering harmful or unsafe prompts. In this paper, we demonstrate how adversaries can exploit LLMs' alignment to implant…

Machine Learning · Computer Science 2025-08-29 Md Abdullah Al Mamun , Ihsen Alouani , Nael Abu-Ghazaleh
‹ Prev 1 4 5 6 7 8 10 Next ›