1 citations · 1 across the 11 of their papers we have counts for
11 papers
SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI
Mana Azarm, Qiyao Wei, Rahul Nambiar
Power-seeking defined as behaviors where AI systems acquire resources, evade oversight, or resist termination beyond task requirements is identified as a key driver of Loss of Cont…
Visualizing token importance for black-box language models
Paulius Rauba, Qiyao Wei, Mihaela van der Schaar
We consider the problem of auditing black-box large language models (LLMs) to ensure they behave reliably when deployed in production settings, particularly in high-stakes domains…
Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?
Matt MacDermott, Qiyao Wei, Rada Djoneva +1
AI systems that output their reasoning in natural language offer an opportunity for safety -- we can \emph{monitor} their chain of thought (CoT) for undesirable reasoning, such as…
Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity
Qiyao Wei, Edward Morrell, Lea Goetz +1
Evaluating the open-form textual responses generated by Large Language Models (LLMs) typically requires measuring the semantic similarity of the response to a (human generated) ref…
Paper Copilot: Tracking the Evolution of Peer Review in AI Conferences
Jing Yang, Qiyao Wei, Jiaxin Pei
The rapid growth of AI conferences is straining an already fragile peer-review system, leading to heavy reviewer workloads, expertise mismatches, inconsistent evaluation standards,…
Event-Aware Sentiment Factors from LLM-Augmented Financial Tweets: A Transparent Framework for Interpretable Quant Trading
Yueyi Wang, Qiyao Wei
In this study, we wish to showcase the unique utility of large language models (LLMs) in financial semantic annotation and alpha signal discovery. Leveraging a corpus of company-re…
Statistical Hypothesis Testing for Auditing Robustness in Language Models
Paulius Rauba, Qiyao Wei, Mihaela van der Schaar
Consider the problem of testing whether the outputs of a large language model (LLM) system change under an arbitrary intervention, such as an input perturbation or changing the mod…
Position: The ML Community Must Build an AI-Augmented Peer-Review Ecosystem
Qiyao Wei, Samuel Holt, Jing Yang +2
Peer review, the bedrock of scientific advancement in machine learning (ML), is strained by a crisis of scale. Exponential growth in manuscript submissions to premier ML venues suc…
Quantifying perturbation impacts for large language models
Paulius Rauba, Qiyao Wei, Mihaela van der Schaar
We consider the problem of quantifying how an input perturbation impacts the outputs of large language models (LLMs), a fundamental task for model reliability and post-hoc interpre…
Defining Expertise: Applications to Treatment Effect Estimation
Alihan Hüyük, Qiyao Wei, Alicia Curth +1
Decision-makers are often experts of their domain and take actions based on their domain knowledge. Doctors, for instance, may prescribe treatments by predicting the likely outcome…
Reference-Limited Compositional Zero-Shot Learning
Siteng Huang, Qiyao Wei, Donglin Wang
Compositional zero-shot learning (CZSL) refers to recognizing unseen compositions of known visual primitives, which is an essential ability for artificial intelligence systems to l…