40 citations · 66 across the 6 of their papers we have counts for
6 papers
Priors in Time: Missing Inductive Biases for Language Model Interpretability
Ekdeep Singh Lubana, Can Rager, Sai Sumedh R. Hindupur +13
Recovering meaningful concepts from language model activations is a central aim of interpretability. While existing feature extraction methods aim to identify concepts that are ind…
Towards Interpretable Soft Prompts
Oam Patel, Jason Wang, Nikhil Shivakumar Nayak +2
Soft prompts have been popularized as a cheap and easy way to improve task-specific LLM performance beyond few-shot prompts. Despite their origin as an automated prompting method,…
Humanity's Last Exam
Long Phan, Alice Gatti, Ziwen Han +1168
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…
Designing a Dashboard for Transparency and Control of Conversational AI
Yida Chen, Aoyu Wu, Trevor DePodesta +9
Conversational LLMs function as black box systems, leaving users guessing about why they see the output they do. This lack of transparency is potentially problematic, especially gi…
Defending Against Unforeseen Failure Modes with Latent Adversarial Training
Stephen Casper, Lennart Schulze, Oam Patel +1
Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack sur…
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
Kenneth Li, Oam Patel, Fernanda Viégas +2
We introduce Inference-Time Intervention (ITI), a technique designed to enhance the "truthfulness" of large language models (LLMs). ITI operates by shifting model activations durin…