相关论文: Trust Me, I'm an Expert: Decoding and Steering Aut…

Emerging research on bias attribution and interpretability have revealed how tokens contribute to biased behavior in language models processing English texts. We build on this line of inquiry by adapting the information-theoretic bias…

Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across models and can be amplified by instruction…

To answer a question, language models often need to integrate prior knowledge learned during pretraining and new information presented in context. We hypothesize that models perform this integration in a predictable way across different…

Inductive reasoning is an essential capability for large language models (LLMs) to achieve higher intelligence, which requires the model to generalize rules from observed facts and then apply them to unseen examples. We present MIRAGE, a…

Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can…

In everyday conversations, humans can take on different roles and adapt their vocabulary to their chosen roles. We explore whether LLMs can take on, that is impersonate, different roles when they generate text in-context. We ask LLMs to…

ML decision-aid systems are increasingly common on the web, but their successful integration relies on people trusting them appropriately: they should use the system to fill in gaps in their ability, but recognize signals that the system…

Can LLMs accurately adjust their confidence when facing opposition? Building on previous studies measuring calibration on static fact-based question-answering tasks, we evaluate Large Language Models (LLMs) in a dynamic, adversarial debate…

Humans use introspection to evaluate their understanding through private internal states inaccessible to external observers. We investigate whether large language models possess similar privileged knowledge about answer correctness,…

Acquiescence bias, i.e. the tendency of humans to agree with statements in surveys, independent of their actual beliefs, is well researched and documented. Since Large Language Models (LLMs) have been shown to be very influenceable by…

Large Language Models (LLMs) can generate content that is as persuasive as human-written text and appear capable of selectively producing deceptive outputs. These capabilities raise concerns about potential misuse and unintended…

Large language models are widely used across domains, yet there are concerns about their factual reliability and biases. Factual knowledge probing offers a systematic means to evaluate these aspects. Most existing benchmarks focus on…

Model editing has been gaining increasing attention over the past few years. For Knowledge Editing in particular, more challenging evaluation datasets have recently been released. These datasets use different methodologies to score the…

Recent work has explored the use of large language models (LLMs) to generate tutoring responses in mathematics, yet it remains unclear how closely their instructional behavior aligns with expert human practice. We analyze a dataset of math…

Expert persona prompting -- assigning roles such as expert in math to language models -- is widely used for task improvement. However, prior work shows mixed results on its effectiveness, and does not consider when and why personas should…

Despite the potential impact of explanations on decision making, there is a lack of research on quantifying their effect on users' choices. This paper presents an experimental protocol for measuring the degree to which positively or…

Masked diffusion language models (MDMs) uniquely support any-order generation, with confidence-based decoding currently serving as the de facto standard inference policy. To optimize for this, recent training schemes attempt to align…

Large Language Models (LLMs) are transforming scholarly tasks like search and summarization, but their reliability remains uncertain. Current evaluation metrics for testing LLM reliability are primarily automated approaches that prioritize…

Large Language Models (LLMs) are seemingly infiltrating every domain, and the legal context is no exception. In this paper, we present the results of three experiments (total N = 288) that investigated lay people's willingness to act upon,…

The emergence of Large Language Models (LLMs) has revealed a growing need for human-AI collaboration, especially in creative decision-making scenarios where trust and reliance are paramount. Through human studies and model evaluations on…