English
Related papers

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

200 papers

Adaptive chatbots that mimic a user's linguistic style can build rapport and engagement, yet unconstrained mimicry risks an agent that feels unstable or sycophantic. We present a computational evaluation framework that makes the core design…

Human-Computer Interaction · Computer Science 2025-10-02 T. James Brandt

People living with dementia (PLwD) often show gradual shifts in how they communicate, becoming less expressive, more repetitive, or drifting off-topic in subtle ways. While caregivers may notice these changes informally, most computational…

Artificial Intelligence · Computer Science 2025-11-21 Joy Lai , Alex Mihailidis

Large Language Models (LLMs) excel at single-turn tasks such as instruction following and summarization, yet real-world deployments require sustained multi-turn interactions where user goals and conversational context persist and evolve. A…

Computation and Language · Computer Science 2025-11-25 Vardhan Dongre , Ryan A. Rossi , Viet Dac Lai , David Seunghyun Yoon , Dilek Hakkani-Tür , Trung Bui

In human-human conversations, Context Tracking deals with identifying important entities and keeping track of their properties and relationships. This is a challenging problem that encompasses several subtasks such as slot tagging,…

Computation and Language · Computer Science 2022-04-27 Ulrich Rückert , Srinivas Sunkara , Abhinav Rastogi , Sushant Prakash , Pranav Khaitan

LLMs are increasingly used as long-running conversational agents, yet every major benchmark evaluating their memory treats user information as static facts to be stored and retrieved. That's the wrong model. People change their minds, and…

Computation and Language · Computer Science 2026-03-26 Praveen Kumar Myakala , Manan Agrawal , Rahul Manche

Production LLM coding agents drift over long sessions: they forget user-specified constraints, slip into mistakes the user already flagged, and confabulate prior agreements. White-box approaches such as persona vectors require model weights…

Cryptography and Security · Computer Science 2026-05-12 Chunxiao Wang

Large language models can represent a variety of personas but typically default to a helpful Assistant identity cultivated during post-training. We investigate the structure of the space of model personas by extracting activation directions…

Computation and Language · Computer Science 2026-01-16 Christina Lu , Jack Gallagher , Jonathan Michala , Kyle Fish , Jack Lindsey

As autonomous coding agents become deeply embedded in software development workflows, their high operational velocity introduces a critical oversight challenge: the accumulating divergence between agentic actions and architectural intent.…

Software Engineering · Computer Science 2026-05-05 Matteo Casserini , Alessandro Facchini , Andrea Ferrario

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…

Computation and Language · Computer Science 2026-04-21 Anmol Goel , Cornelius Emde , Sangdoo Yun , Seong Joon Oh , Martin Gubri

Qualitative research studies often employ a contextual inquiry, or a field study that involves in-depth observation and interviews of a small sample of study participants, in-situ, to gain a robust understanding of the reasons and…

Human-Computer Interaction · Computer Science 2023-12-14 Rishika Dwaraghanath , Rahul Majethia , Sanjana Gautam

The quality of AI-generated output is often attributed to prompting technique, but extensive empirical observation suggests that context completeness may be more strongly associated with output quality. This paper introduces Context…

Artificial Intelligence · Computer Science 2026-04-07 Elias Calboreanu

Prior research indicates that users prefer assistive technologies whose personalities align with their own. This has sparked interest in automatic personality perception (APP), which aims to predict an individual's perceived personality…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-28 Alice Zhang , Skanda Muralidhar , Daniel Gatica-Perez , Mathew Magimai-Doss

As language models (LMs) are increasingly deployed as autonomous agents, their robust adherence to human-assigned objectives becomes crucial for safe operation. When these agents operate independently for extended periods without human…

Artificial Intelligence · Computer Science 2025-05-06 Rauno Arike , Elizabeth Donoway , Henning Bartsch , Marius Hobbhahn

User interactions with language models vary due to static properties of the user (trait) and the specific context of the interaction (state). However, existing persona datasets (like PersonaChat, PANDORA etc.) capture only trait, and ignore…

Computation and Language · Computer Science 2026-05-08 Tamunotonye Harry , Ivoline Ngong , Chima Nweke , Yuanyuan Feng , Joseph Near

Personalized alignments for individual users have been a long-standing goal in large language models (LLMs). We introduce Drift, a novel framework that personalizes LLMs at decoding time with implicit user preferences. Traditional…

Computation and Language · Computer Science 2025-05-09 Minbeom Kim , Kang-il Lee , Seongho Joo , Hwaran Lee , Thibaut Thonet , Kyomin Jung

Egocentric AI assistants in real-world settings must process multi-modal inputs (video, audio, text), respond in real time, and retain evolving long-term memory. However, existing benchmarks typically evaluate these abilities in isolation,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Jiaqi Yan , Ruilong Ren , Jingren Liu , Shuning Xu , Ling Wang , Yiheng Wang , Xinlin Zhong , Yun Wang , Long Zhang , Xiangyu Chen , Changzhi Sun , Jixiang Luo , Dell Zhang , Hao Sun , Chi Zhang , Xuelong Li

With the increasing deployment of large language models (LLMs) in affective agents and AI systems, maintaining a consistent and authentic LLM personality becomes critical for user trust and engagement. However, existing work overlooks a…

Computation and Language · Computer Science 2026-02-03 Jiongchi Yu , Yuhan Ma , Xiaoyu Zhang , Junjie Wang , Qiang Hu , Chao Shen , Xiaofei Xie

Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend…

A model that avoids stereotypes in a lab benchmark may not avoid them in deployment. We show that measured bias shifts dramatically when prompts mention different places, times, or audiences -- no adversarial prompting required. We…

Computation and Language · Computer Science 2026-01-16 Abhinaba Basu , Pavan Chakraborty

A major impediment to the transition to context-aware machine translation is the absence of good evaluation metrics and test sets. Sentences that require context to be translated correctly are rare in test sets, reducing the utility of…

Computation and Language · Computer Science 2023-11-07 Rachel Wicks , Matt Post
‹ Prev 1 2 3 10 Next ›