40 citations · 116 across the 13 of their papers we have counts for
4 papers · 1 filter
Sparse Reward Subsystem in Large Language Models
Guowei Xu, Mert Yuksekgonul, James Zou
Recent studies show that LLM hidden states encode reward-related information, such as answer correctness and model confidence. However, existing approaches typically fit black-box…
TextGrad: Automatic "Differentiation" via Text
Mert Yuksekgonul, Federico Bianchi, Joseph Boen +4
AI is undergoing a paradigm shift, with breakthroughs achieved by systems orchestrating multiple large language models (LLMs) and other complex components. As a result, developing…
Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
Mert Yuksekgonul, Varun Chandrasekaran, Erik Jones +5
We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text. We propose modeling factual queries as constrain…
GPT detectors are biased against non-native English writers
Weixin Liang, Mert Yuksekgonul, Yining Mao +2
The rapid adoption of generative language models has brought about substantial advancements in digital communication, while simultaneously raising concerns regarding the potential…