191 citations · 238 across the 7 of their papers we have counts for
7 papers
Measuring Sparse Autoencoder Feature Sensitivity
Claire Tian, Katherine Tian, Nathan Hu
Sparse Autoencoder (SAE) features have become essential tools for mechanistic interpretability research. SAE features are typically characterized by examining their activating exam…
Fine-tuning Language Models for Factuality
Katherine Tian, Eric Mitchell, Huaxiu Yao +2
The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet languag…
Multimodal Image-Text Matching Improves Retrieval-based Chest X-Ray Report Generation
Jaehwan Jeong, Katherine Tian, Andrew Li +7
Automated generation of clinically accurate radiology reports can improve patient care. Previous report generation methods that rely on image captioning models often generate incoh…
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
Katherine Tian, Eric Mitchell, Allan Zhou +5
A trustworthy real-world prediction system should produce well-calibrated confidence scores; that is, its confidence in an answer should be indicative of the likelihood that the an…
Doubly robust nearest neighbors in factor models
Raaz Dwivedi, Caleb Chin, Sabina Tomkins +3
We introduce and analyze an improved variant of nearest neighbors (NN) for estimation with missing data in latent factor models. We consider a matrix completion problem with missin…
Counterfactual inference in sequential experiments
Raaz Dwivedi, Katherine Tian, Sabina Tomkins +3
We consider after-study statistical inference for sequentially designed experiments wherein multiple units are assigned treatments for multiple time points using treatment policies…
Technical Note on Transcription Factor Motif Discovery from Importance Scores (TF-MoDISco) version 0.5.6.5
Avanti Shrikumar, Katherine Tian, Žiga Avsec +5
TF-MoDISco (Transcription Factor Motif Discovery from Importance Scores) is an algorithm for identifying motifs from basepair-level importance scores computed on genomic sequence d…