相关论文: Contextual Moral Value Alignment Through Context-B…

Recent advancements in Large Language Models (LLMs) have transformed many fields including scientific discovery, content generation, biomedical text mining, and educational technology. However, the substantial requirements for training…

The wide exploration of large language models (LLMs) raises the awareness of alignment between healthcare stakeholder preferences and model outputs. This alignment becomes a crucial foundation to empower the healthcare workflow effectively,…

Instruction-tuned Large Language Models (LLMs) are increasingly deployed as AI Assistants in firms for support in cognitive tasks. These AI assistants carry embedded perspectives which influence factors across the firm including…

Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression…

Value alignment of Large Language Models (LLMs) requires us to empirically measure these models' actual, acquired representation of value. Among the characteristics of value representation in humans is that they distinguish among value of…

Decision-making agents based on pre-trained Large Language Models (LLMs) are increasingly being deployed across various domains of human activity. While their applications are currently rather specialized, several research efforts are…

Large Language Models (LLMs) have revolutionised the capability of AI models in comprehending and generating natural language text. They are increasingly being used to empower and deploy agents in real-world scenarios, which make decisions…

This article introduces an innovative architecture designed to declaratively combine Large Language Models (LLMs) with shared histories, and triggers to identify the most appropriate LLM for a given task. Our approach is general and…

Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently using to understand…

The emergent capabilities of Large Language Models (LLMs) have made it crucial to align their values with those of humans. However, current methodologies typically attempt to assign value as an attribute to LLMs, yet lack attention to the…

AI alignment, the challenge of ensuring AI systems act in accordance with human values, has emerged as a critical problem in the development of systems such as foundation models and recommender systems. Still, the current dominant approach,…

Agents based on Large Language Models (LLMs) are increasingly permeating various domains of human production and life, highlighting the importance of aligning them with human values. The current alignment of AI systems primarily focuses on…

With the development of Large Language Models (LLMs) in consulting, their role in moral decision-making has become prominent. However, existing research predominantly consider AI as an independent "moral agent" adhering to the "Human-AI…

General-purpose automatic speech recognition (ASR) systems do not always perform well in goal-oriented dialogue. Existing ASR correction methods rely on prior user data or named entities. We extend correction to tasks that have no prior…

In high-stakes AI-supported decisions, considerations are not purely technical but involve moral judgments about fairness, responsibility, and harm. While prior research has focused mainly on functional or behavioral alignment, this paper…

As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safety concern. Existing benchmarks, focused on static,…

Developing moral awareness in intelligent systems has shifted from a topic of philosophical inquiry to a critical and practical issue in artificial intelligence over the past decades. However, automated inference of everyday moral…

Large language models (LLMs) have made remarkable progress in generating fluent text, but they still face a critical challenge of contextual misalignment in long-term and dynamic dialogue. When human users omit premises, simplify…

Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions…

We evaluate the moral alignment of LLMs with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judgments across 200+ countries, we develop a cross-lingual…