English
Related papers

Related papers: Get my drift? Catching LLM Task Drift with Activat…

200 papers

Despite the fact that large language models (LLMs) show exceptional skill in instruction following tasks, this strength can turn into a vulnerability when the models are required to disregard certain instructions. Instruction-following…

Computation and Language · Computer Science 2025-08-12 Yerin Hwang , Yongil Kim , Jahyun Koo , Taegwan Kang , Hyunkyung Bae , Kyomin Jung

Long-term interaction with LLM-based systems may produce alignment drift: a gradual process in which system outputs become less constrained by the user's current message and more shaped by prior interaction history, while still appearing…

Human-Computer Interaction · Computer Science 2026-05-19 Xintong Yao

Data search for scientific research is more complex than a simple web search. The emergence of large language models (LLMs) and their applicability for scientific tasks offers new opportunities for researchers who are looking for data,…

Digital Libraries · Computer Science 2025-10-29 Christin Katharina Kreutz , Anja Perry , Tanja Friedrich

Data contamination, i.e., the presence of test data from downstream tasks in the training data of large language models (LLMs), is a potential major issue in measuring LLMs' real effectiveness on other tasks. We propose a straightforward…

Computation and Language · Computer Science 2024-02-23 Shahriar Golchin , Mihai Surdeanu

Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, because of their instruction-following capabilities and…

Cryptography and Security · Computer Science 2025-10-07 Yulin Chen , Haoran Li , Yuan Sui , Yufei He , Yue Liu , Yangqiu Song , Bryan Hooi

Recently, people have suffered from LLM hallucination and have become increasingly aware of the reliability gap of LLMs in open and knowledge-intensive tasks. As a result, they have increasingly turned to search-augmented LLMs to mitigate…

Computation and Language · Computer Science 2026-02-10 Yu Yan , Sheng Sun , Mingfeng Li , Zheming Yang , Chiwei Zhu , Fei Ma , Benfeng Xu , Min Liu , Qi Li

A trained ML model is deployed on another `test' dataset where target feature values (labels) are unknown. Drift is distribution change between the training and deployment data, which is concerning if model performance changes. For a…

Applications · Statistics 2022-09-07 Samuel Ackerman , Eitan Farchi , Orna Raz , Marcel Zalmanovici , Parijat Dube

To combat the misuse of Large Language Models (LLMs), many recent studies have presented LLM-generated-text detectors with promising performance. When users instruct LLMs to generate texts, the instruction can include different constraints…

Computation and Language · Computer Science 2024-10-02 Ryuto Koike , Masahiro Kaneko , Naoaki Okazaki

A growing demand is witnessed in both industry and academia for employing Deep Learning (DL) in various domains to solve real-world problems. Deep Reinforcement Learning (DRL) is the application of DL in the domain of Reinforcement Learning…

Software Engineering · Computer Science 2021-11-30 Amin Nikanjam , Mohammad Mehdi Morovati , Foutse Khomh , Houssem Ben Braiek

When intelligent agents communicate to accomplish shared goals, how do these goals shape the agents' language? We study the dynamics of learning in latent language policies (LLPs), in which instructor agents generate natural-language…

Computation and Language · Computer Science 2021-04-16 Athul Paul Jacob , Mike Lewis , Jacob Andreas

LLMs' performance on complex tasks is still unsatisfactory. A key issue is that presently LLMs learn in a data-driven schema, while the instructions about these complex tasks are both scarce and hard to collect or construct. On the…

Machine Learning · Computer Science 2024-10-21 Yang Zhao , Li Du , Xiao Ding , Kai Xiong , Ting Liu , Bing Qin

Index tuning is critical for the performance of modern database systems. Industrial index tuners, such as the Database Tuning Advisor (DTA) developed for Microsoft SQL Server, rely on the "what-if" API provided by the query optimizer to…

Databases · Computer Science 2026-05-12 Xiaoying Wang , Wentao Wu , Vivek Narasayya , Surajit Chaudhuri

Large language models (LLMs) tuned for safety often avoid acknowledging demographic differences, even when such acknowledgment is factually correct (e.g., ancestry-based disease incidence) or contextually justified (e.g., religious hiring…

Computation and Language · Computer Science 2026-04-21 Ziwen Pan , Zihan Liang , Jad Kabbara , Ali Emami

In applying deep learning for malware classification, it is crucial to account for the prevalence of malware evolution, which can cause trained classifiers to fail on drifted malware. Existing solutions to address concept drift use active…

Cryptography and Security · Computer Science 2024-12-23 Adrian Shuai Li , Arun Iyengar , Ashish Kundu , Elisa Bertino

Large language models (LLMs) show potential as simulators of human behavior, offering a scalable way to study responses to interventions. However, because LLMs are trained largely on observational data, interventions in experiments with…

Computation and Language · Computer Science 2026-05-21 Victoria Lin , Taedong Yun , Maja Matarić , John Canny , Arthur Gretton , Alexander D'Amour

Large language models (LLMs) have demonstrated great performance across various benchmarks, showing potential as general-purpose task solvers. However, as LLMs are typically trained on vast amounts of data, a significant concern in their…

Computation and Language · Computer Science 2025-05-13 Yujuan Fu , Ozlem Uzuner , Meliha Yetisgen , Fei Xia

Data rights owners can detect unauthorized data use in large language model (LLM) training by querying with proprietary samples. Often, superior performance (e.g., higher confidence or lower loss) on a sample relative to the untrained data…

Cryptography and Security · Computer Science 2026-05-29 Muxing Li , Zesheng Ye , Sharon Li , Feng Liu

LLMs trained in the understanding of programming syntax are now providing effective assistance to developers and are being used in programming education such as in generation of coding problem examples or providing code explanations. A key…

Artificial Intelligence · Computer Science 2024-11-19 Yanggyu Lee , Suchae Jeong , Jihie Kim

Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool…

Computation and Language · Computer Science 2025-02-27 Changle Qu , Sunhao Dai , Xiaochi Wei , Hengyi Cai , Shuaiqiang Wang , Dawei Yin , Jun Xu , Ji-Rong Wen

Large Language Model (LLM) agents are increasingly being deployed as conversational assistants capable of performing complex real-world tasks through tool integration. This enhanced ability to interact with external systems and process…

Cryptography and Security · Computer Science 2024-12-24 Feiran Jia , Tong Wu , Xin Qin , Anna Squicciarini
‹ Prev 1 2 3 10 Next ›