相关论文: Do Linear Probes Generalize Better in Persona Coor…

Large language models (LLMs) are increasingly used as proxies for human judgment in computational social science, yet their ability to reproduce patterns of susceptibility to misinformation remains unclear. We test whether LLM-simulated…

Mechanistic approaches to deception in large language models (LLMs) often rely on "lie detectors", that is, truth probes trained to identify internal representations of model outputs as false. The lie detector approach to LLM deception…

Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic…

As AI systems become more intelligent and their behavior becomes more challenging to assess, they may learn to game the flaws of human feedback instead of genuinely striving to follow instructions; however, this risk can be mitigated by…

The text produced by language models (LMs) can exhibit specific `behaviors,' such as a failure to follow alignment training, that we hope to detect and react to during deployment. Identifying these behaviors can often only be done post…

Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of actions with real-world impacts beyond text generation. While persona-induced biases in text generation are well documented, their effects on agent task…

Large Language Model (LLM)-based multi-agent systems are increasingly used to simulate human interactions and solve collaborative tasks. A common practice is to assign agents with personas to encourage behavioral diversity. However, this…

Human action recognition models often rely on background cues rather than human movement and pose to make predictions, a behavior known as background bias. We present a systematic analysis of background bias across classification models,…

We find that correct-to-incorrect sycophancy signals are most linearly separable within multi-head attention activations. Motivated by the linear representation hypothesis, we train linear probes across the residual stream, multilayer…

Steering vectors are a lightweight method to control language model behavior by adding a learned bias to the activations at inference time. Although steering demonstrates promising performance, recent work shows that it can be unreliable or…

Large Language Model (LLM) agents are increasingly deployed in settings where they interact with a wide variety of people, including users who are unclear, impatient, or reluctant to share information. However, collecting real interaction…

Models that are learned from real-world data are often biased because the data used to train them is biased. This can propagate systemic human biases that exist and ultimately lead to inequitable treatment of people, especially minorities.…

It is widely accepted in the mode connectivity literature that when two neural networks are trained similarly on the same data, they are connected by a path through parameter space over which test set accuracy is maintained. Under some…

Neural language models (LMs) can be used to evaluate the truth of factual statements in two ways: they can be either queried for statement probabilities, or probed for internal representations of truthfulness. Past work has found that these…

We study generalization in deep learning by appealing to complexity measures originally developed in approximation and information theory. While these concepts are challenged by the high-dimensional and data-defined nature of deep learning,…

Bounding boxes are often used to communicate automatic object detection results to humans, aiding humans in a multitude of tasks. We investigate the relationship between bounding box localization errors and human task performance. We use…

The goal of selective prediction is to allow an a model to abstain when it may not be able to deliver a reliable prediction, which is important in safety-critical contexts. Existing approaches to selective prediction typically require…

Contemporary research in social sciences increasingly utilizes state-of-the-art generative language models to annotate or generate content. While these models achieve benchmark-leading performance on common language tasks, their application…

Smart assistants increasingly act proactively, yet mistimed or intrusive behavior often causes users to lose trust and disable these features. Learning user preferences for proactive assistance is difficult because real-world studies are…

People naturally vary in their annotations for subjective questions and some of this variation is thought to be due to the person's sociodemographic characteristics. LLMs have also been used to label data, but recent work has shown that…