papers

Publications (27)

cs.CL2023

Character-level Chinese Backpack Language Models

Hao Sun, John Hewitt

The Backpack is a Transformer alternative shown to improve interpretability in English language modeling by decomposing predictions into a weighted sum of token sense components. H…

cs.LG2021

Probing artificial neural networks: insights from neuroscience

Anna A. Ivanova, John Hewitt, Noga Zaslavsky

A major challenge in both neuroscience and machine learning is the development of useful tools for understanding complex information processing systems. One such tool is probes, i.…

astro-ph.HE2015

New Identification of the Mixed-Morphology Supernova Remnant G298.6-0.0 with Possible Gamma-ray Association

Aya Bamba, Makoto Sawada, Yuto Nakano +4

We present an X-ray analysis on the Galactic supernova remnant (SNR) G298.6-0.0 with Suzaku. The X-ray image shows a center-filled structure inside the radio shell, implying this S…

cs.CL2023

Lost in the Middle: How Language Models Use Long Contexts

Nelson F. Liu, Kevin Lin, John Hewitt +4

While recent language models have the ability to take long contexts as input, relatively little is known about how well they use longer context. We analyze the performance of langu…

cs.CL2021

Conditional probing: measuring usable information beyond a baseline

John Hewitt, Kawin Ethayarajh, Percy Liang +1

Probing experiments investigate the extent to which neural representations make properties -- like part-of-speech -- predictable. One suggests that a representation encodes a prope…

cs.CL2026

Improving Parametric Knowledge Access in Reasoning Language Models

Melody Ma, John Hewitt

We study reasoning for accessing world knowledge stored in a language model's parameters. For example, recalling that Canberra is Australia's capital may benefit from thinking thro…

cs.CL2025

Neologism Learning for Controllability and Self-Verbalization

John Hewitt, Oyvind Tafjord, Robert Geirhos +1

Humans invent new words when there is a rising demand for a new useful concept (e.g., doomscrolling). We explore and validate a similar idea in our communication with LLMs: introdu…

cs.CL2020

Finding Universal Grammatical Relations in Multilingual BERT

Ethan A. Chi, John Hewitt, Christopher D. Manning

Recent work has found evidence that Multilingual BERT (mBERT), a transformer-based multilingual masked language model, is capable of zero-shot cross-lingual transfer, suggesting th…

cs.CL2020

The EOS Decision and Length Extrapolation

Benjamin Newman, John Hewitt, Percy Liang +1

Extrapolation to unseen sequence lengths is a challenge for neural generative models of language. In this work, we characterize the effect on length extrapolation of a modeling dec…

cs.CL2019

Designing and Interpreting Probes with Control Tasks

John Hewitt, Percy Liang

Probes, supervised models trained to predict properties (like parts-of-speech) from representations (like ELMo), have achieved high accuracy on a range of linguistic tasks. But doe…

cs.CL2018

XNMT: The eXtensible Neural Machine Translation Toolkit

Graham Neubig, Matthias Sperber, Xinyi Wang +10

This paper describes XNMT, the eXtensible Neural Machine Translation toolkit. XNMT distin- guishes itself from other open-source NMT toolkits by its focus on modular code design, w…

cs.CL2026

Subliminal Steering: Stronger Encoding of Hidden Signals

George Morgulis, John Hewitt

Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model. Prior work has b…

cs.CL2019

Simple, Fast, Accurate Intent Classification and Slot Labeling for Goal-Oriented Dialogue Systems

Arshit Gupta, John Hewitt, Katrin Kirchhoff

With the advent of conversational assistants, like Amazon Alexa, Google Now, etc., dialogue systems are gaining a lot of traction, especially in industrial setting. These systems t…

cs.CL2023

Backpack Language Models

John Hewitt, John Thickstun, Christopher D. Manning +1

We present Backpacks: a new neural architecture that marries strong modeling performance with an interface for interpretability and control. Backpacks learn multiple non-contextual…

cs.CL2024

Instruction Following without Instruction Tuning

John Hewitt, Nelson F. Liu, Percy Liang +1

Instruction tuning commonly means finetuning a language model on instruction-response pairs. We discover two forms of adaptation (tuning) that are deficient compared to instruction…

cs.CL2024

Learning Translations via Matrix Completion

Derry Wijaya, Brendan Callahan, John Hewitt +4

Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel corpora. We model this task as a matrix completion problem, and present an effectiv…

cs.LG2022

On the Opportunities and Risks of Foundation Models

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli +111

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.…

cs.CL2022

JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset

Ruth-Ann Armstrong, John Hewitt, Christopher Manning

JamPatoisNLI provides the first dataset for natural language inference in a creole language, Jamaican Patois. Many of the most-spoken low-resource languages are creoles. These lang…

cs.CL2021

Refining Targeted Syntactic Evaluation of Language Models

Benjamin Newman, Kai-Siang Ang, Julia Gong +1

Targeted syntactic evaluation of subject-verb number agreement in English (TSE) evaluates language models' syntactic knowledge using hand-crafted minimal pairs of sentences that di…

cs.CL2022

Truncation Sampling as Language Model Desmoothing

John Hewitt, Christopher D. Manning, Percy Liang

Long samples of text from neural language models can be of poor quality. Truncation sampling algorithms--like top- or top- -- address this by setting some words' probabilitie…

cs.CL2024

Model Editing with Canonical Examples

John Hewitt, Sarah Chen, Lanruo Lora Xie +3

We introduce model editing with canonical examples, a setting in which (1) a single learning example is provided per desired behavior, (2) evaluation is performed exclusively out-o…

cs.CL2020

RNNs can generate bounded hierarchical languages with optimal memory

John Hewitt, Michael Hahn, Surya Ganguli +2

Recurrent neural networks empirically generate natural language with high syntactic fidelity. However, their success is not well-understood theoretically. We provide theoretical in…

astro-ph.HE2023

The Third Fermi Large Area Telescope Catalog of Gamma-ray Pulsars

David A. Smith, Philippe Bruel, Colin J. Clark +156

We present 294 pulsars found in GeV data from the Large Area Telescope (LAT) on the Fermi Gamma-ray Space Telescope. Another 33 millisecond pulsars (MSPs) discovered in deep radio…

cs.CL2023

Closing the Curious Case of Neural Text Degeneration

Matthew Finlayson, John Hewitt, Alexander Koller +2

Despite their ubiquity in language generation, it remains unknown why truncation sampling heuristics like nucleus sampling are so effective. We provide a theoretical explanation fo…

cs.AI2025

Because we have LLMs, we Can and Should Pursue Agentic Interpretability

Been Kim, John Hewitt, Neel Nanda +2

The era of Large Language Models (LLMs) presents a new opportunity for interpretability--agentic interpretability: a multi-turn conversation with an LLM wherein the LLM proactively…

cs.CL2025

We Can't Understand AI Using our Existing Vocabulary

John Hewitt, Robert Geirhos, Been Kim

This position paper argues that, in order to understand AI, we cannot rely on our existing vocabulary of human words. Instead, we should strive to develop neologisms: new words tha…

astro-ph.HE2016

Discovery of X-ray Emission from the Galactic Supernova Remnant G32.8-0.1 with Suzaku

Aya Bamba, Yukikatsu Terada, John Hewitt +6

We present the first dedicated X-ray study of the supernova remnant (SNR) G32.8-0.1 (Kes 78) with Suzaku. X-ray emission from the whole SNR shell has been detected for the first ti…