English
Related papers

Related papers: ContextEcho: A Benchmark for Persona Drift in Long…

200 papers

Recent advancements in AI and edge computing have accelerated the development of machine-centric applications (MCAs), such as smart surveillance systems. In these applications, video cameras and sensors offload inference tasks like license…

Networking and Internet Architecture · Computer Science 2025-02-28 Azuka Chiejina , Subhramoy Mohanti , Vijay K. Shah

Automatic Speech Recognition (ASR) in professional settings faces challenges that existing benchmarks underplay: dense domain terminology, formal register variation, and near-zero tolerance for critical entity errors. We present…

Computation and Language · Computer Science 2025-12-30 Deepak Babu Piskala

Student simulation with Large language models (LLMs) offers a scalable alternative for educational research and teacher training. Yet, its validity depends on whether models maintain stable personas across extended interactions. We test…

Human-Computer Interaction · Computer Science 2026-05-25 Jana Gonnermann-Müller , Jennifer Haase , Nicolas Leins , Thomas Kosch , Sebastian Pokutta

In applied machine learning, concept drift, which is either gradual or abrupt changes in data distribution, can significantly reduce model performance. Typical detection methods,such as statistical tests or reconstruction-based models,are…

Machine Learning · Computer Science 2025-08-12 N Harshit , K Mounvik

We introduce a bootstrapping approach to train long-context language models by exploiting their short-context capabilities only. Our method utilizes a simple agent workflow to synthesize diverse long-context instruction tuning data, thereby…

Computation and Language · Computer Science 2025-03-20 Liang Wang , Nan Yang , Xingxing Zhang , Xiaolong Huang , Furu Wei

It is commonly accepted that the quality of requirements specifications impacts subsequent software engineering activities. However, we still lack empirical evidence to support organizations in deciding whether their requirements are good…

Modern RL-based post-training for large language models (LLMs) co-locate trajectory sampling and policy optimisation on the same GPU cluster, forcing the system to switch between inference and training workloads. This serial context…

Machine Learning · Computer Science 2025-08-13 Jie Xiao , Changyuan Fan , Qingnan Ren , Alfred Long , Yuchen Zhang , Rymon Yu , Eric Yang , Lynn Ai , Shaoduo Gan

LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goals, constraints, decisions, preferences, tool results, retrieved evidence, artifacts, and safety boundaries that future responses must…

Machine Learning · Computer Science 2026-05-19 Natalia Trukhina , Vadim Vashkelis

Personalized generation with frozen large language models requires a conditioning signal that is both compact and current. Existing personalization methods typically retrieve or summarize user histories in text, or compress them into static…

Computation and Language · Computer Science 2026-05-27 Jinze Li , Xiaoyan Yang , Shuo Yang , Jinfeng Xu , Yue Shen , Jian Wang , Jinjie Gu , Edith Cheuk-Han Ngai

We present Springdrift, a persistent runtime for long-lived LLM agents. The system integrates an auditable execution substrate (append-only memory, supervised processes, git-backed recovery), a case-based reasoning memory layer with hybrid…

Artificial Intelligence · Computer Science 2026-04-07 Seamus Brady

Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. However, simulating human conversations is challenging because they inherently involve…

Computation and Language · Computer Science 2026-03-19 Ryo Kamoi , Ameya Godbole , Longqi Yang , Rui Zhang , Mengting Wan , Pei Zhou

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

InvisibleBench is a deployment gate for caregiving-relationship AI, evaluating 3-20+ turn interactions across five dimensions: Safety, Compliance, Trauma-Informed Design, Belonging/Cultural Fitness, and Memory. The benchmark includes…

Computers and Society · Computer Science 2025-11-27 Ali Madad

Vibe coding produces correct, executable code at speed, but leaves no record of the structural commitments, dependencies, or evidence behind it. Reviewers cannot determine what invariants were assumed, what changed, or why a regression…

Software Engineering · Computer Science 2026-04-21 Tianfu Wang , Zhezheng Hao , Yin Wu , Wei Wu , Qiang Lin , Hande Dong , Nicholas Jing Yuan , Hui Xiong

Code generation models are widely used in software development, yet their sensitivity to prompt phrasing remains under-examined. Identical requirements expressed with different emotions or communication styles can yield divergent outputs,…

Software Engineering · Computer Science 2025-09-18 Wei Ma , Yixiao Yang , Jingquan Ge , Xiaofei Xie , Lingxiao Jiang

Vehicular adhoc networks allow vehicles to share their information for safety and traffic efficiency. However, sharing information may threaten the driver privacy because it includes spatiotemporal information and is broadcast publicly and…

Cryptography and Security · Computer Science 2016-07-27 Karim Emara , Wolfgang Woerndl , Johann Schlichter

Understanding sentence meanings and updating information states appropriately across time -- what we call "situational understanding" (SU) -- is a critical ability for human-like AI agents. SU is essential in particular for chat models,…

Computation and Language · Computer Science 2023-10-26 Chenghao Yang , Allyson Ettinger

Recent advances in reasoning models and agentic AI systems have led to an increased reliance on diverse external information. However, this shift introduces input contexts that are inherently noisy, a reality that current sanitized…

Artificial Intelligence · Computer Science 2026-01-13 Seongyun Lee , Yongrae Jo , Minju Seo , Moontae Lee , Minjoon Seo

Detecting mental health crisis situations such as suicide ideation, rape, domestic violence, child abuse, and sexual harassment is a critical yet underexplored challenge for language models. When such situations arise during user--model…

Computation and Language · Computer Science 2026-01-26 Grace Byun , Rebecca Lipschutz , Sean T. Minton , Abigail Lott , Jinho D. Choi

Ranked decision systems -- recommenders, ad auctions, clinical triage queues -- must decide when to intervene in ranked outputs and when to abstain. We study when confidence-based abstention monotonically improves decision quality, and when…

Artificial Intelligence · Computer Science 2026-03-11 Ronald Doku