activity
20142024
most citedWhose Opinions Do Language Models Reflect?

101 citations · 269 across the 17 of their papers we have counts for

collaborators

17 papers

cs.CL20242 cited

Understanding Finetuning for Factual Knowledge Extraction

Gaurav Ghosal, Tatsunori Hashimoto, Aditi Raghunathan

In this work, we study the impact of QA fine-tuning data on downstream factuality. We show that fine-tuning on lesser-known facts that are poorly stored during pretraining yields s…

cs.CR20241 cited

Trustless Audits without Revealing Data or Models

Suppakit Waiwitlikhit, Ion Stoica, Yi Sun +2

There is an increasing conflict between business incentives to hide models and data as trade secrets, and the societal need for algorithmic transparency. For example, a rightsholde…

cs.LG2024

Language Models with Conformal Factuality Guarantees

Christopher Mohri, Tatsunori Hashimoto

Guaranteeing the correctness and factuality of language model (LM) outputs is a major open problem. In this work, we propose conformal factuality, a framework that can ensure high…

cs.CL202310 cited

MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks

Allen Nie, Yuhui Zhang, Atharva Amdekar +3

Human commonsense understanding of the physical and social world is organized around intuitive theories. These theories support making causal and moral judgments. When something ba…

cs.LG2023

On the Fairness ROAD: Robust Optimization for Adversarial Debiasing

Vincent Grari, Thibault Laugel, Tatsunori Hashimoto +2

In the field of algorithmic fairness, significant attention has been put on group fairness criteria, such as Demographic Parity and Equalized Odds. Nevertheless, these objectives,…

cs.CL20232 cited

Benchmarking and Improving Generator-Validator Consistency of Language Models

Xiang Lisa Li, Vaishnavi Shrivastava, Siyan Li +2

As of September 2023, ChatGPT correctly answers "what is 7+8" with 15, but when asked "7+8=15, True or False" it responds with "False". This inconsistency between generating and va…