Related papers: Alignment of Language Agents
In the rapidly evolving field of artificial intelligence (AI) agents, designing the agent's characteristics is crucial for shaping user experience. This workshop aims to establish a research community focused on AI agent persona design for…
Researchers across cognitive, neuro-, and computer sciences increasingly reference human-like artificial intelligence and neuroAI. However, the scope and use of the terms are often inconsistent. Contributed research ranges widely from…
To safely interact with humans, AI agents must both know our norms and consider them during planning. However, such norm-guided planning has been less explored, only within communities of artificial agents, and has ignored the dynamic…
Existing alignment research is dominated by concerns about safety and preventing harm: safeguards, controllability, and compliance. This paradigm of alignment parallels early psychology's focus on mental illness: necessary but incomplete.…
In today's digital society, personalization has become a crucial aspect of software applications, significantly impacting user experience and engagement. A new wave of intelligent user interfaces, such as AI-based conversational agents, has…
This paper explores the advancements in making large language models (LLMs) more human-like. We focus on techniques that enhance natural language understanding, conversational coherence, and emotional intelligence in AI systems. The study…
This position paper argues that AI agents should be regulated by the extent to which they operate autonomously. AI agents with long-term planning and strategic capabilities can pose significant risks of human extinction and irreversible…
Building socially-intelligent AI agents (Social-AI) is a multidisciplinary, multimodal research goal that involves creating agents that can sense, perceive, reason about, learn from, and respond to affect, behavior, and cognition of other…
Understanding the actions of both humans and artificial intelligence (AI) agents is important before modern AI systems can be fully integrated into our daily life. In this paper, we show that, despite their current huge success, deep…
Background: Value alignment in computer science research is often used to refer to the process of aligning artificial intelligence with humans, but the way the phrase is used often lacks precision. Objectives: In this paper, we conduct a…
Advanced reasoning models with agentic capabilities (AI agents) are deployed to interact with humans and to solve sequential decision-making problems under (approximate) utility functions and internal models. When such problems have…
This study investigates malicious AI Assistants' manipulative traits and whether the behaviours of malicious AI Assistants can be detected when interacting with human-like simulated users in various decision-making contexts. We also examine…
Can AI agents deal with hard choices -- cases where options are incommensurable because multiple objectives are pursued simultaneously? Adopting a technologically engaged approach distinct from existing philosophical literature, I submit…
This position paper's primary goal is to provoke thoughtful discussion about the relationship between bias and fundamental properties of large language models. I do this by seeking to convince the reader that harmful biases are an…
It is incredibly easy for a system designer to misspecify the objective for an autonomous system ("robot''), thus motivating the desire to have the robot learn the objective from human behavior instead. Recent work has suggested that people…
Artificial Intelligence (AI) has a communication problem. XAI methods have been used to make AI more understandable and helped resolve some of the transparency issues that inhibit AI's broader usability. However, user evaluation studies…
Understanding the decisions made and actions taken by increasingly complex AI system remains a key challenge. This has led to an expanding field of research in explainable artificial intelligence (XAI), highlighting the potential of…
Explainability techniques are rapidly being developed to improve human-AI decision-making across various cooperative work settings. Consequently, previous research has evaluated how decision-makers collaborate with imperfect AI by…
Human perception, memory and decision-making are impacted by tens of cognitive biases and heuristics that influence our actions and decisions. Despite the pervasiveness of such biases, they are generally not leveraged by today's Artificial…
As increasingly capable large language model (LLM)-based agents are developed, the potential harms caused by misalignment and loss of control grow correspondingly severe. To address these risks, we propose an approach that directly measures…