English
Related papers

Related papers: Neural Transparency: Mechanistic Interpretability …

200 papers

Large Language Models (LLMs) are being increasingly integrated into software systems, offering powerful capabilities but also raising concerns about fairness. Existing fairness benchmarks, however, focus on stereotype-specific associations,…

Software Engineering · Computer Science 2026-04-08 Gianmario Voria , Martina De Lucia , Alessandra Raia , Andrea De Lucia , Gemma Catolino , Fabio Palomba

The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed…

Computation and Language · Computer Science 2026-04-14 Hwan Chang , Yonghyun Jun , Hwanhee Lee

The increasing prevalence of Artificial Intelligence (AI) in safety-critical contexts such as air-traffic control leads to systems that are practical and efficient, and to some extent explainable to humans to be trusted and accepted. The…

Computers and Society · Computer Science 2023-06-28 Sabine Theis , Sophie Jentzsch , Fotini Deligiannaki , Charles Berro , Arne Peter Raulf , Carmen Bruder

With large language models (LLMs) becoming increasingly prevalent in daily life, so too has the tendency to attribute to them human-like minds and emotions, or anthropomorphize them. Here, we investigate dimensions people use to…

We investigate whether Large Language Models (LLMs) exhibit human-like cognitive patterns under four established frameworks from psychology: Thematic Apperception Test (TAT), Framing Bias, Moral Foundations Theory (MFT), and Cognitive…

Artificial Intelligence · Computer Science 2025-12-12 Akash Kundu , Rishika Goswami

This paper studies how parents want to moderate children's interactions with Generative AI chatbots, with the goal of informing the design of future GenAI parental control tools. We first used an LLM to generate synthetic child-GenAI…

Human-Computer Interaction · Computer Science 2026-03-13 John Driscoll , Yulin Chen , Viki Shi , Izak Vucharatavintara , Yaxing Yao , Haojian Jin

Anthropomorphizing conversational technology is a natural human tendency. Today, the anthropomorphic metaphor is overly reinforced across intelligent tools. Large Language Models (LLMs) are particularly anthropomorphized through interface…

Human-Computer Interaction · Computer Science 2026-03-06 Jianna So , Connie Cheng , Sonia Krishna Murthy

Nowadays, neural network (NN) and deep learning (DL) techniques are widely adopted in many applications, including recommender systems. Given the sparse and stochastic nature of collaborative filtering (CF) data, recent works have…

Information Retrieval · Computer Science 2024-07-03 Giuseppe Serra , Peter Tino , Zhao Xu , Xin Yao

People navigate complex environments using cues, heuristics, and other strategies, which are often adaptive in stable settings. However, as AI increasingly permeates society's information environments, those become more adaptive and…

Human-Computer Interaction · Computer Science 2026-02-03 Ezequiel Lopez-Lopez , Christoph M. Abels , Philipp Lorenz-Spreen , Stephan Lewandowsky , Stefan M. Herzog

As the use of interactive AI systems becomes increasingly prevalent in our daily lives, it is crucial to understand how individuals feel when interacting with such systems. In this work, we investigate the comfort level of individuals when…

Human-Computer Interaction · Computer Science 2023-03-01 Yi Ru Wang , Jiafei Duan , Sidharth Talia , Hao Zhu

LLMs are increasingly being deployed as chatbots, but today's interfaces offer little to no friction: users interact through seamless conversations that conceal when the model is drifting, hallucinating or failing. This lack of transparency…

Human-Computer Interaction · Computer Science 2026-01-21 Riju Marwah , Vishal Pallagani , Ritvik Garimella , Amit Sheth

As artificial intelligence systems increasingly inform high-stakes decisions across sectors, transparency has become foundational to responsible and trustworthy AI implementation. Leveraging our role as a leading institute in advancing AI…

Machine Learning · Computer Science 2025-08-01 Dhanesh Ramachandram , Himanshu Joshi , Judy Zhu , Dhari Gandhi , Lucas Hartman , Ananya Raval

LLM-based chatbots are now being specifically designed to facilitate social companionship, even romantic relationships, incorporating features that parallel human relationship dynamics. This has led a subset of users to form romantic…

Human-Computer Interaction · Computer Science 2025-11-26 Paula Ebner , Jessica Szczuka

Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goals. Progress in this field thus promises to provide greater…

Mechanistic interpretability is the program of explaining what AI systems are doing in terms of their internal mechanisms. I analyze some aspects of the program, along with setting out some concrete challenges and assessing progress to…

Artificial Intelligence · Computer Science 2025-01-28 David J. Chalmers

AI chatbots have made vast strides in technology improvement in recent years and are already operational in many industries. Advanced Natural Language Processing techniques, based on deep networks, efficiently process user requests to carry…

Computation and Language · Computer Science 2021-05-17 Nathan Dolbir , Triyasha Dastidar , Kaushik Roy

Human-LLM conversations are increasingly becoming more pervasive in peoples' professional and personal lives, yet many users still struggle to elicit helpful responses from LLM Chatbots. One of the reasons for this issue is users' lack of…

Computation and Language · Computer Science 2025-06-26 Rupak Sarkar , Bahareh Sarrafzadeh , Nirupama Chandrasekaran , Nagu Rangan , Philip Resnik , Longqi Yang , Sujay Kumar Jauhar

Recent work by Anthropic on Mechanistic interpretability claims to understand and control Large Language Models by extracting human-interpretable features from their neural activation patterns using sparse autoencoders (SAEs). If…

Machine Learning · Computer Science 2026-01-07 Raphael Ronge , Markus Maier , Frederick Eberhardt

Recent breakthroughs in natural language processing (NLP) have permitted the synthesis and comprehension of coherent text in an open-ended way, therefore translating the theoretical algorithms into practical applications. The large language…

Computation and Language · Computer Science 2023-05-30 Terry Yue Zhuo , Yujin Huang , Chunyang Chen , Zhenchang Xing

The number of robots deployed in our daily surroundings is ever-increasing. Even in the industrial set-up, the use of coworker robots is increasing rapidly. These cohabitant robots perform various tasks as instructed by co-located human…

Robotics · Computer Science 2020-09-01 Pradip Pramanick , Chayan Sarkar , Indrajit Bhattacharya