Related papers: Understanding Annotator Safety Policy with Interpr…

Methods and applications are inextricably linked in science, and in particular in the domain of text-as-data. In this paper, we examine one such text-as-data application, an established economic index that measures economic policy…

Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model…

Multi-annotator learning traditionally aggregates diverse annotations to approximate a single ground truth, treating disagreements as noise. However, this paradigm faces fundamental challenges: subjective tasks often lack absolute ground…

A key concern with the concept of "alignment" is the implicit question of "alignment to what?". AI systems are increasingly used across the world, yet safety alignment is often focused on homogeneous monolingual settings. Additionally,…

To design effective digital interventions, experimenters face the challenge of learning decision policies that balance multiple objectives using offline data. Often, they aim to develop policies that maximize goal outcomes, while ensuring…

Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information. Automatically notifying users whether their queries leak privacy and which phrases leak what private…

Generative large language models (LLMs) can be a powerful tool for augmenting text annotation procedures, but their performance varies across annotation tasks due to prompt quality, text data idiosyncrasies, and conceptual difficulty.…

A cautious interpretation of AI regulations and policy in the EU and the USA place explainability as a central deliverable of compliant AI systems. However, from a technical perspective, explainable AI (XAI) remains an elusive and complex…

Concept Bottleneck Models (CBMs) provide inherent interpretability by first mapping input samples to high-level semantic concepts, followed by a combination of these concepts for the final classification. However, the annotation of…

As frontier AI models are deployed globally, it is essential that their behaviour remains safe and reliable across diverse linguistic and cultural contexts. To examine how current model safeguards hold up in such settings, participants from…

Understanding how different stakeholders perceive risks in AI systems is essential for their responsible deployment. This paper presents a framework for stakeholder-grounded risk assessment by using LLMs, acting as judges to predict and…

Although the synthesis of programs encoding policies often carries the promise of interpretability, systematic evaluations were never performed to assess the interpretability of these policies, likely because of the complexity of such an…

In this position paper, we discuss the potential for leveraging LLMs as interactive research tools to facilitate collaboration between human coders and AI to effectively annotate online risk data at scale. Collaborative human-AI labeling is…

Social annotation platforms enable student engagement by integrating discussions directly into course materials. However, in large online courses, the sheer volume of comments can overwhelm students and impede learning. This paper…

This paper presents a logic programming-based framework for policy-aware autonomous agents that can reason about potential penalties for non-compliance and act accordingly. While prior work has primarily focused on ensuring compliance, our…

Interpretability provides a means for humans to verify aspects of machine learning (ML) models and empower human+ML teaming in situations where the task cannot be fully automated. Different contexts require explanations with different…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing…

Reliable reward models (RMs) are critical for ensuring the safe alignment of large language models (LLMs). However, current RM evaluation methods focus solely on preference perception accuracies in given specific scenarios, obscuring the…

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…