English
Related papers

Related papers: TRACEALIGN -- Tracing the Drift: Attributing Align…

200 papers

Alignment faking is a form of strategic deception in AI in which models selectively comply with training objectives when they infer that they are in training, while preserving different behavior outside training. The phenomenon was first…

Large Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tuning can bypass these protocols, underscoring the need to…

Machine Learning · Computer Science 2025-02-04 Ching-Chia Kao , Chia-Mu Yu , Chun-Shien Lu , Chu-Song Chen

Large language models (LLMs) have shown impressive few-shot generalization on many tasks via in-context learning (ICL). Despite their success in showing such emergent abilities, the scale and complexity of larger models also lead to…

Computation and Language · Computer Science 2025-06-03 Chengwei Qin , Wenhan Xia , Fangkai Jiao , Chen Chen , Yuchen Hu , Bosheng Ding , Ruirui Chen , Shafiq Joty

We present TraceFix, a verification-first pipeline for Large Language Model (LLM) multi-agent coordination. An agent synthesizes a protocol topology as a structured intermediate representation (IR) from a task description, generates PlusCal…

Artificial Intelligence · Computer Science 2026-05-11 Shuren Xia , Qiwei Li , Taqiya Ehsan , Jorge Ortiz

Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implicitly harmful data. Even some seemingly benign data can inadvertently steer a model…

Computation and Language · Computer Science 2026-05-15 Zhanhao Hu , Xiao Huang , Patrick Mendoza , Emad A. Alghamdi , Basel Alomair , Raluca Ada Popa , David Wagner

Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe outputs. In this paper, we introduce and evaluate a new…

Cryptography and Security · Computer Science 2026-02-19 Jean-Charles Noirot Ferrand , Yohan Beugin , Eric Pauley , Ryan Sheatsley , Patrick McDaniel

Instruction tuning has emerged as the key in aligning large language models (LLMs) with specific task instructions, thereby mitigating the discrepancy between the next-token prediction objective and users' actual goals. To reduce the labor…

Computation and Language · Computer Science 2024-04-10 Zifeng Wang , Chun-Liang Li , Vincent Perot , Long T. Le , Jin Miao , Zizhao Zhang , Chen-Yu Lee , Tomas Pfister

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

Computation and Language · Computer Science 2025-09-16 Xue Zhang , Yunlong Liang , Fandong Meng , Songming Zhang , Yufeng Chen , Jinan Xu , Jie Zhou

Large language models (LLMs) are foundational explorations to artificial general intelligence, yet their alignment with human values via instruction tuning and preference learning achieves only superficial compliance. Here, we demonstrate…

Computation and Language · Computer Science 2025-06-04 Jiawei Lian , Jianhong Pan , Lefan Wang , Yi Wang , Shaohui Mei , Lap-Pui Chau

Large language models (LLMs) have shown tremendous success in following user instructions and generating helpful responses. Nevertheless, their robustness is still far from optimal, as they may generate significantly inconsistent responses…

Computation and Language · Computer Science 2024-03-25 Yukun Zhao , Lingyong Yan , Weiwei Sun , Guoliang Xing , Shuaiqiang Wang , Chong Meng , Zhicong Cheng , Zhaochun Ren , Dawei Yin

Large language models (LLMs) are trained through multi-stage pipelines over heterogeneous data sources, yet developers lack a principled way to pinpoint the specific data responsible for an observed behavior. This lack of observability…

Computation and Language · Computer Science 2026-03-19 Wenjie Jacky Mo , Qin Liu , Xiaofei Wen , Wenxuan Zhou , Zhe Zhao , Muhao Chen

The rise of large language models (LLMs) has significantly influenced the quality of information in decision-making systems, leading to the prevalence of AI-generated content and challenges in detecting misinformation and managing…

Computation and Language · Computer Science 2024-10-08 Cheng Jiayang , Chunkit Chan , Qianqian Zhuang , Lin Qiu , Tianhang Zhang , Tengxiao Liu , Yangqiu Song , Yue Zhang , Pengfei Liu , Zheng Zhang

As large language models (LLMs) are deployed in high-stakes domains like healthcare, understanding how well their decision-making aligns with human preferences and values becomes crucial, especially when we recognize that there is no single…

Computation and Language · Computer Science 2024-10-01 Isaac Kohane

Schema linking is a critical bottleneck in applying existing Text-to-SQL models to real-world, large-scale, multi-database environments. Through error analysis, we identify two major challenges in schema linking: (1) Database Retrieval:…

Computation and Language · Computer Science 2025-09-09 Yihan Wang , Peiyu Liu , Xin Yang

Large language models (LLMs) are becoming increasingly prevalent in modern software systems, interfacing between the user and the Internet to assist with tasks that require advanced language understanding. To accomplish these tasks, the LLM…

Cryptography and Security · Computer Science 2025-07-04 Sizhe Chen , Arman Zharmagambetov , Saeed Mahloujifar , Kamalika Chaudhuri , David Wagner , Chuan Guo

Network traffic classification (NTC) models often suffer severe performance degradation when deployed in real-world environments due to distribution shifts caused by changing network conditions. Existing robustness-enhancing approaches are…

Machine Learning · Computer Science 2026-05-19 Tongze Wang , Xiaohui Xie , Wenduo Wang , Chuyi Wang , Yong Cui

Financial institutions deploy Large Language Models (LLMs) for reconciliations, regulatory reporting, and client communications, but nondeterministic outputs (output drift) undermine auditability and trust. We quantify drift across five…

Machine Learning · Computer Science 2025-11-12 Raffi Khatchadourian , Rolando Franco

Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on…

Artificial Intelligence · Computer Science 2025-12-23 Qinglin Zeng , Jing Yang , Keze Wang

Code Large Language Models (Code LLMs) are being increasingly employed in real-life applications, so evaluating them is critical. While the conventional accuracy evaluates the performance of Code LLMs on a set of individual tasks, their…

Machine Learning · Computer Science 2024-02-27 Marcus J. Min , Yangruibo Ding , Luca Buratti , Saurabh Pujar , Gail Kaiser , Suman Jana , Baishakhi Ray

Large Language Models (LLMs) have exhibited exceptional performance in software engineering yet face challenges in adapting to continually evolving code knowledge, particularly regarding the frequent updates of third-party library APIs.…

Computation and Language · Computer Science 2025-06-19 Chenlong Wang , Zhaoyang Chu , Zhengxiang Cheng , Xuyi Yang , Kaiyue Qiu , Yao Wan , Zhou Zhao , Xuanhua Shi , Dongping Chen