papers

Publications (12)

cs.CL2024

Decision-Oriented Dialogue for Human-AI Collaboration

Jessy Lin, Nicholas Tomlin, Jacob Andreas +1

We describe a class of tasks called decision-oriented dialogues, in which AI assistants such as large language models (LMs) must collaborate with one or more humans via natural lan…

cs.CV2018

Black-box Adversarial Attacks with Limited Queries and Information

Andrew Ilyas, Logan Engstrom, Anish Athalye +1

Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker only has query access to the model. In practice,…

cs.SE2023

InCoder: A Generative Model for Code Infilling and Synthesis

Daniel Fried, Armen Aghajanyan, Jessy Lin +7

Code is seldom written in a single left-to-right pass and is instead repeatedly edited and refined. We introduce InCoder, a unified generative model that can perform program synthe…

cs.LG2022

UniMASK: Unified Inference in Sequential Decision Problems

Micah Carroll, Orr Paradise, Jessy Lin +8

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same…

cs.CL2022

Automatic Correction of Human Translations

Jessy Lin, Geza Kovacs, Aditya Shastry +2

We introduce translation error correction (TEC), the task of automatically correcting human-generated translations. Imperfections in machine translations (MT) have long motivated s…

cs.CL2025

Learning Facts at Scale with Active Reading

Jessy Lin, Vincent-Pierre Berges, Xilun Chen +3

LLMs are known to store vast amounts of knowledge in their parametric memory. However, learning and recalling facts from this memory is known to be unreliable, depending largely on…

cs.CL2022

Inferring Rewards from Language in Context

Jessy Lin, Daniel Fried, Dan Klein +1

In classic instruction following, language like "I'd like the JetBlue flight" maps to actions (e.g., selecting that flight). However, language also conveys information about a user…

cs.IR2024

CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval

Yizhou Chi, Jessy Lin, Kevin Lin +1

Users often make ambiguous requests that require clarification. We study the problem of asking clarification questions in an information retrieval setting, where systems often face…

cs.CL2025

Continual Learning via Sparse Memory Finetuning

Jessy Lin, Luke Zettlemoyer, Gargi Ghosh +4

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where u…

cs.CV2018

Query-Efficient Black-box Adversarial Examples (superceded)

Andrew Ilyas, Logan Engstrom, Anish Athalye +1

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to advers…

cs.CL2024

Learning to Model the World with Language

Jessy Lin, Yuqing Du, Olivia Watkins +4

To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to e…

cs.LG2022

Towards Flexible Inference in Sequential Decision Problems via Bidirectional Transformers

Micah Carroll, Jessy Lin, Orr Paradise +8

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same…