13 citations · 23 across the 9 of their papers we have counts for
9 papers
Position: It's Time to Optimize LLMs for Self-Consistency
Itamar Pres, Belinda Z. Li, Laura Ruis +6
Despite ever-increasing sophistication in language model (LM) pre- and post-training pipelines, many important failures persist: models overcondition on user framing ("sycophancy")…
Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision
Zifan Carl Guo, Laura Ruis, Jacob Andreas +1
When does training language models (LMs) to generate explanations of their predictions yield faithful introspection, rather than superficial imitation? We study LMs trained to expl…
Training Language Models to Explain Their Own Computations
Belinda Z. Li, Zifan Carl Guo, Vincent Huang +2
Can language models (LMs) learn to faithfully describe their internal computations? Are they better able to describe themselves than other models? We study the extent to which LMs'…
(How) Do Language Models Track State?
Belinda Z. Li, Zifan Carl Guo, Jacob Andreas
Transformer language models (LMs) exhibit behaviors -- from storytelling to code generation -- that seem to require tracking the unobserved state of an evolving world. How do they…
Survival of the Fittest Representation: A Case Study with Modular Addition
Xiaoman Delores Ding, Zifan Carl Guo, Eric J. Michaud +2
When a neural network can learn multiple distinct algorithms to solve a task, how does it "choose" between them during training? To approach this question, we take inspiration from…
Algorithmic progress in language models
Anson Ho, Tamay Besiroglu, Ege Erdil +6
We investigate the rate at which algorithms for pre-training language models have improved since the advent of deep learning. Using a dataset of over 200 language model evaluations…
Opening the AI black box: program synthesis via mechanistic interpretability
Eric J. Michaud, Isaac Liao, Vedang Lad +7
We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the le…
Universal Neurons in GPT2 Language Models
Wes Gurnee, Theo Horsley, Zifan Carl Guo +5
A basic question within the emerging field of mechanistic interpretability is the degree to which neural networks learn the same underlying mechanisms. In other words, are neural m…
Measuring the Success of Diffusion Models at Imitating Human Artists
Stephen Casper, Zifan Guo, Shreya Mogulothu +5
Modern diffusion models have set the state-of-the-art in AI image generation. Their success is due, in part, to training on Internet-scale data which often includes copyrighted wor…