papers

Publications (106)

cs.LG2020

A Deep Factorization of Style and Structure in Fonts

Nikita Srivatsan, Jonathan T. Barron, Dan Klein +1

We propose a deep factorization model for typographic analysis that disentangles content from style. Specifically, a variational inference procedure factors each training glyph int…

cs.CL2019

Multilingual Constituency Parsing with Self-Attention and Pre-Training

Nikita Kitaev, Steven Cao, Dan Klein

We show that constituency parsing benefits from unsupervised pre-training across a variety of languages and a range of pre-training conditions. We first compare the benefits of no…

cs.CV2018

Speaker-Follower Models for Vision-and-Language Navigation

Daniel Fried, Ronghang Hu, Volkan Cirik +7

Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few h…

cs.CR2025

GenSIaC: Toward Security-Aware Infrastructure-as-Code Generation with Large Language Models

Yikun Li, Matteo Grella, Daniel Nahmias +5

In recent years, Infrastructure as Code (IaC) has emerged as a critical approach for managing and provisioning IT infrastructure through code and automation. IaC enables organizati…

cs.CL2017

Improving Neural Parsing by Disentangling Model Combination and Reranking Effects

Daniel Fried, Mitchell Stern, Dan Klein

Recent work has proposed several generative neural models for constituency parsing that achieve state-of-the-art results. Since direct search in these generative models is difficul…

cs.CL2025

LangProBe: a Language Programs Benchmark

Shangyin Tan, Lakshya A Agrawal, Arnav Singhvi +6

Composing language models (LMs) into multi-step language programs and automatically optimizing their modular prompts is now a mainstream paradigm for building AI systems, but the t…

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.CL2016

Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints

Greg Durrett, Taylor Berg-Kirkpatrick, Dan Klein

We present a discriminative model for single-document summarization that integrally combines compression and anaphoricity constraints. Our model selects textual units to include in…

cs.CL2018

What's Going On in Neural Constituency Parsers? An Analysis

David Gaddy, Mitchell Stern, Dan Klein

A number of differences have emerged between modern and classic approaches to constituency parsing in recent years, with structural components like grammars and feature-rich lexico…

cs.LG2017

Modular Multitask Reinforcement Learning with Policy Sketches

Jacob Andreas, Dan Klein, Sergey Levine

We describe a framework for multitask deep reinforcement learning guided by policy sketches. Sketches annotate tasks with sequences of named subtasks, providing information about h…

cs.CL2023

Poisoning Language Models During Instruction Tuning

Alexander Wan, Eric Wallace, Sheng Shen +1

Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetuned on datasets that contain user-submitted examples, e.g., FLAN aggregates numerous open-source datasets and…

cs.CL2023

DOC: Improving Long Story Coherence With Detailed Outline Control

Kevin Yang, Dan Klein, Nanyun Peng +1

We propose the Detailed Outline Control (DOC) framework for improving long-range plot coherence when automatically generating several-thousand-word-long stories. DOC consists of tw…

cs.CL2025

Enough Coin Flips Can Make LLMs Act Bayesian

Ritwik Gupta, Rodolfo Corona, Jiaxin Ge +4

Large language models (LLMs) exhibit the ability to generalize given few-shot examples in their input prompt, an emergent capability known as in-context learning (ICL). We investig…

cs.CL2022

Neural Unsupervised Reconstruction of Protolanguage Word Forms

Andre He, Nicholas Tomlin, Dan Klein

We present a state-of-the-art neural approach to the unsupervised reconstruction of ancient word forms. Previous work in this domain used expectation-maximization to predict simple…

cs.CL2024

Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination

Eve Fleisig, Genevieve Smith, Madeline Bossi +3

We present a large-scale study of linguistic bias exhibited by ChatGPT covering ten dialects of English (Standard American English, Standard British English, and eight widely spoke…

cs.CL2022

Re3: Generating Longer Stories With Recursive Reprompting and Revision

Kevin Yang, Yuandong Tian, Nanyun Peng +1

We consider the problem of automatically generating longer stories of over two thousand words. Compared to prior work on shorter stories, long-range plot coherence and relevance ar…

cs.CL2025

Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions

Eve Fleisig, Matthias Orlikowski, Philipp Cimiano +1

For machine learning datasets to accurately represent diverse opinions in a population, they must preserve variation in data labels while filtering out spam or low-quality response…

cs.CL2023

Decomposing Complex Queries for Tip-of-the-tongue Retrieval

Kevin Lin, Kyle Lo, Joseph E. Gonzalez +1

When re-finding items, users who forget or are uncertain about identifying details often rely on creative strategies for expressing their information needs -- complex queries that…

cs.CV2026

Open-Ended CT Volume Segmentation with Weak Supervision from Language

Sanjay Subramanian, Junwei Yu, Zirui Wang +5

We introduce a method for training a text-conditioned segmentation model for CT scans, which combines voxel-level supervision with coarse but scalable slice-level supervision from…

cs.CL2021

Task-Oriented Dialogue as Dataflow Synthesis

Semantic Machines, Jacob Andreas, John Bufe +43

We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends th…

cs.CL2024

American Sign Language Handshapes Reflect Pressures for Communicative Efficiency

Kayo Yin, Terry Regier, Dan Klein

Communicative efficiency is a key topic in linguistics and cognitive psychology, with many studies demonstrating how the pressure to communicate with minimal effort guides the form…

cs.CL2023

Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL

Ruiqi Zhong, Charlie Snell, Dan Klein +1

Can non-programmers annotate natural language utterances with complex programs that represent their meaning? We introduce APEL, a framework in which non-programmers select among ca…

cs.CL2026

Composing Policy Gradients and Prompt Optimization for Language Model Programs

Noah Ziems, Dilara Soylu, Lakshya A Agrawal +10

Group Relative Policy Optimization (GRPO) has proven to be an effective tool for post-training language models (LMs). However, AI systems are increasingly expressed as modular prog…

cs.CL2026

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Lakshya A Agrawal, Shangyin Tan, Dilara Soylu +14

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often requir…

cs.CL2023

Goal Driven Discovery of Distributional Differences via Language Descriptions

Ruiqi Zhong, Peter Zhang, Steve Li +3

Mining large corpora can generate useful discoveries but is time-consuming for humans. We formulate a new task, D5, that automatically discovers differences between two large corpo…

cs.CL2021

Calibrate Before Use: Improving Few-Shot Performance of Language Models

Tony Z. Zhao, Eric Wallace, Shi Feng +2

GPT-3 can perform numerous tasks when provided a natural language prompt that contains a few training examples. We show that this type of few-shot learning can be unstable: the cho…

cs.CL2017

Effective Inference for Generative Neural Parsing

Mitchell Stern, Daniel Fried, Dan Klein

Generative neural models have recently achieved state-of-the-art results for constituency parsing. However, without a feasible search procedure, their use has so far been limited t…

cs.CL2018

Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing

Daniel Fried, Dan Klein

Dynamic oracles provide strong supervision for training constituency parsers with exploration, but must be custom defined for a given parser's transition system. We explore using a…

cs.CL2018

Unified Pragmatic Models for Generating and Following Instructions

Daniel Fried, Jacob Andreas, Dan Klein

We show that explicit pragmatic inference aids in correctly generating and following natural language instructions for complex, sequential tasks. Our pragmatics-enabled models reas…

cs.CR2025

An ontological lens on attack trees: Toward adequacy and interoperability

Ítalo Oliveira, Stefano M. Nicoletti, Gal Engelberg +3

Attack Trees (AT) are a popular formalism for security analysis. They are meant to display an attacker's goal decomposed into attack steps needed to achieve it and compute certain…

cs.CL2016

Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks

Matthew Francis-Landau, Greg Durrett, Dan Klein

A key challenge in entity linking is making effective use of contextual information to disambiguate mentions that might refer to different entities in different contexts. We presen…

cs.CL2017

Learning with Latent Language

Jacob Andreas, Dan Klein, Sergey Levine

The named concepts and compositional operators present in natural language provide a rich source of information about the kinds of abstractions humans use to navigate the world. Ca…

cs.CL2023

Improving Pacing in Long-Form Story Planning

Yichen Wang, Kevin Yang, Xiaoming Liu +1

Existing LLM-based systems for writing long-form stories or story outlines frequently suffer from unnatural pacing, whether glossing over important events or over-elaborating on in…

cs.CL2021

Constructing Taxonomies from Pretrained Language Models

Catherine Chen, Kevin Lin, Dan Klein

We present a method for constructing taxonomic trees (e.g., WordNet) using pretrained language models. Our approach is composed of two modules, one that predicts parenthood relatio…

cs.CL2015

Neural CRF Parsing

Greg Durrett, Dan Klein

This paper describes a parsing model that combines the exact dynamic programming of CRF parsing with the rich nonlinear featurization of neural net approaches. Our model is structu…

cs.CL2024

Ghostbuster: Detecting Text Ghostwritten by Large Language Models

Vivek Verma, Eve Fleisig, Nicholas Tomlin +1

We introduce Ghostbuster, a state-of-the-art system for detecting AI-generated text. Our method works by passing documents through a series of weaker language models, running a str…

cs.CL2020

Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers

Zhuohan Li, Eric Wallace, Sheng Shen +4

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and in…

cs.AI2025

Measuring General Intelligence with Generated Games

Vivek Verma, David Huang, William Chen +2

We present gg-bench, a collection of game environments designed to evaluate general reasoning capabilities in language models. Unlike most static benchmarks, gg-bench is a data gen…

cs.CL2017

Parsing with Traces: An Algorithm and a Structural Representation

Jonathan K. Kummerfeld, Dan Klein

General treebank analyses are graph structured, but parsers are typically restricted to tree structures for efficiency and modeling reasons. We propose a new representation and alg…

cs.CL2024

Efficacy of Language Model Self-Play in Non-Zero-Sum Games

Austen Liao, Nicholas Tomlin, Dan Klein

Game-playing agents like AlphaGo have achieved superhuman performance through self-play, which is theoretically guaranteed to yield optimal policies in competitive games. However,…

cs.CV2025

Pose Priors from Language Models

Sanjay Subramanian, Evonne Ng, Lea Müller +3

Language is often used to describe physical interaction, yet most 3D human pose estimation methods overlook this rich source of information. We bridge this gap by leveraging large…

cs.LG2024

The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labels

Eve Fleisig, Su Lin Blodgett, Dan Klein +1

Longstanding data labeling practices in machine learning involve collecting and aggregating labels from multiple annotators. But what should we do when annotators disagree? Though…

cs.CL2018

Constituency Parsing with a Self-Attentive Encoder

Nikita Kitaev, Dan Klein

We demonstrate that replacing an LSTM encoder with a self-attentive architecture can lead to improvements to a state-of-the-art discriminative constituency parser. The use of atten…

cs.CL2024

Which One? Leveraging Context Between Objects and Multiple Views for Language Grounding

Chancharik Mitra, Abrar Anwar, Rodolfo Corona +3

When connecting objects and their language referents in an embodied 3D environment, it is important to note that: (1) an object can be better characterized by leveraging comparativ…

cs.CL2024

When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Tasks

Eve Fleisig, Rediet Abebe, Dan Klein

Though majority vote among annotators is typically used for ground truth labels in natural language processing, annotator disagreement in tasks such as hate speech detection may re…

cs.CL2017

Alignment-based compositional semantics for instruction following

Jacob Andreas, Dan Klein

This paper describes an alignment-based model for interpreting natural language instructions in context. We approach instruction following as a search over plans, scoring sequences…

cs.CL2023

The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding

Hao Fang, Anusha Balakrishnan, Harsh Jhamtani +7

In a real-world dialogue system, generated text must be truthful and informative while remaining fluent and adhering to a prescribed style. Satisfying these constraints simultaneou…

cs.CL2023

Incorporating Worker Perspectives into MTurk Annotation Practices for NLP

Olivia Huang, Eve Fleisig, Dan Klein

Current practices regarding data collection for natural language processing on Amazon Mechanical Turk (MTurk) often rely on a combination of studies on data quality and heuristics…

cs.CL2023

Revisiting Entropy Rate Constancy in Text

Vivek Verma, Nicholas Tomlin, Dan Klein

The uniform information density (UID) hypothesis states that humans tend to distribute information roughly evenly across an utterance or discourse. Early evidence in support of the…

cs.CL2026

optimize_anything: A Universal API for Optimizing any Text Parameter

Lakshya A Agrawal, Donghyun Lee, Shangyin Tan +11

Can a single LLM-based optimization system match specialized tools across fundamentally different domains? We show that when optimization problems are formulated as improving a tex…

eess.AS2021

An Improved Model for Voicing Silent Speech

David Gaddy, Dan Klein

In this paper, we present an improved model for voicing silent speech, where audio is synthesized from facial electromyography (EMG) signals. To give our model greater flexibility…

cs.CL2022

Automated Crossword Solving

Eric Wallace, Nicholas Tomlin, Albert Xu +4

We present the Berkeley Crossword Solver, a state-of-the-art approach for automatically solving crossword puzzles. Our system works by generating answer candidates for each crosswo…

cs.CL2020

Semantic Evaluation for Text-to-SQL with Distilled Test Suites

Ruiqi Zhong, Tao Yu, Dan Klein

We propose test suite accuracy to approximate semantic accuracy for Text-to-SQL models. Our method distills a small test suite of databases that achieves high code coverage for the…

cs.CL2020

Semantic Scaffolds for Pseudocode-to-Code Generation

Ruiqi Zhong, Mitchell Stern, Dan Klein

We propose a method for program generation based on semantic scaffolds, lightweight structures representing the high-level semantic and syntactic composition of a program. By first…

cs.CL2021

Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level

Ruiqi Zhong, Dhruba Ghosh, Dan Klein +1

Larger language models have higher accuracy on average, but are they better on every single instance (datapoint)? Some work suggests larger models have higher out-of-distribution r…

cs.CL2020

Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference

Nikita Kitaev, Dan Klein

We present a constituency parsing algorithm that, like a supertagger, works by assigning labels to each word in a sentence. In order to maximally leverage current neural architectu…

cs.CL2022

Understanding Game-Playing Agents with Natural Language Annotations

Nicholas Tomlin, Andre He, Dan Klein

We present a new dataset containing 10K human-annotated games of Go and show how these natural language annotations can be used as a tool for model interpretability. Given a board…

cs.CL2016

Learning to Compose Neural Networks for Question Answering

Jacob Andreas, Marcus Rohrbach, Trevor Darrell +1

We describe a question answering model that applies to both images and structured knowledge bases. The model uses natural language strings to automatically assemble neural networks…

cs.CL2021

Approximating How Single Head Attention Learns

Charlie Snell, Ruiqi Zhong, Dan Klein +1

Why do models often attend to salient words, and how does this evolve throughout training? We approximate model training as a two stage process: early on in training when the atten…

cs.CL2020

Multilingual Alignment of Contextual Word Representations

Steven Cao, Nikita Kitaev, Dan Klein

We propose procedures for evaluating and strengthening contextual embedding alignment and show that they are useful in analyzing and improving multilingual BERT. In particular, aft…

cs.CL2021

A Streaming Approach For Efficient Batched Beam Search

Kevin Yang, Violet Yao, John DeNero +1

We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our s…

cs.CL2023

PREADD: Prefix-Adaptive Decoding for Controlled Text Generation

Jonathan Pei, Kevin Yang, Dan Klein

We propose Prefix-Adaptive Decoding (PREADD), a flexible method for controlled text generation. Unlike existing methods that use auxiliary expert models to control for attributes,…

cs.CL2024

Re-evaluating the Need for Multimodal Signals in Unsupervised Grammar Induction

Boyi Li, Rodolfo Corona, Karttikeya Mangalam +7

Are multimodal inputs necessary for grammar induction? Recent work has shown that multimodal training inputs can improve grammar induction. However, these improvements are based on…

cs.CL2022

Describing Differences between Text Distributions with Natural Language

Ruiqi Zhong, Charlie Snell, Dan Klein +1

How do two distributions of texts differ? Humans are slow at answering this, since discovering patterns might require tediously reading through hundreds of samples. We propose to a…

cs.CL2024

Discovering Latent Knowledge in Language Models Without Supervision

Collin Burns, Haotian Ye, Dan Klein +1

Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we tra…

cs.CL2022

Learning by Distilling Context

Charlie Snell, Dan Klein, Ruiqi Zhong

Language models significantly benefit from context tokens, such as prompts or scratchpads. They perform better when prompted with informative instructions, and they acquire new rea…

cs.CL2023

Modular Visual Question Answering via Code Generation

Sanjay Subramanian, Medhini Narasimhan, Kushal Khangaonkar +6

We present a framework that formulates visual question answering as modular code generation. In contrast to prior work on modular approaches to VQA, our approach requires no additi…

cs.CL2017

Abstract Syntax Networks for Code Generation and Semantic Parsing

Maxim Rabinovich, Mitchell Stern, Dan Klein

Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax netwo…

cs.CL2019

Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation

Ronghang Hu, Daniel Fried, Anna Rohrbach +3

Vision-and-Language Navigation (VLN) requires grounding instructions, such as "turn right and stop at the door", to routes in a visual environment. The actual grounding can connect…

cs.CL2019

Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following

David Gaddy, Dan Klein

We consider the problem of learning to map from natural language instructions to state transitions (actions) in a data-efficient manner. Our method takes inspiration from the idea…

cs.CL2018

Translating Neuralese

Jacob Andreas, Anca Dragan, Dan Klein

Several approaches have recently been proposed for learning decentralized deep multiagent policies that coordinate via a differentiable communication channel. While these policies…

cs.CL2022

Voxel-informed Language Grounding

Rodolfo Corona, Shizhan Zhu, Dan Klein +1

Natural language applied to natural 2D images describes a fundamentally 3D world. We present the Voxel-informed Language Grounder (VLG), a language grounding model that leverages 3…

cs.CL2021

FUDGE: Controlled Text Generation With Future Discriminators

Kevin Yang, Dan Klein

We propose Future Discriminators for Generation (FUDGE), a flexible and modular method for controlled text generation. Given a pre-existing model G for generating text from a distr…

cs.CL2021

Detoxifying Language Models Risks Marginalizing Minority Voices

Albert Xu, Eshaan Pathak, Eric Wallace +3

Language models (LMs) must be both safe and equitable to be responsibly deployed in practice. With safety in mind, numerous detoxification techniques (e.g., Dathathri et al. 2020;…

cond-mat.mes-hall2022

Giant chirality-induced spin-selectivity of polarons

Dan Klein, Karen Michaeli

The chirality-induced spin selectivity (CISS) effect gives rise to strongly spin-dependent transport through many organic molecules and structures. Its discovery raises fascinating…

cs.CL2017

Analogs of Linguistic Structure in Deep Representations

Jacob Andreas, Dan Klein

We investigate the compositional structure of message vectors computed by a deep network trained on a communication game. By comparing truth-conditional representations of encoder-…

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.CL2019

Cross-Domain Generalization of Neural Constituency Parsers

Daniel Fried, Nikita Kitaev, Dan Klein

Neural parsers obtain state-of-the-art results on benchmark treebanks for constituency parsing -- but to what degree do they generalize to other domains? We present three results a…

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.CL2024

RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment

Kevin Yang, Dan Klein, Asli Celikyilmaz +2

We propose Reinforcement Learning from Contrastive Distillation (RLCD), a method for aligning language models to follow principles expressed in natural language (e.g., to be more h…

cs.IT2022

Towards an Ontology-Driven Approach for Process-Aware Risk Propagation

Gal Engelberg, Mattia Fumagalli, Adrian Kuboszek +3

The rapid development of cyber-physical systems creates an increasing demand for a general approach to risk, especially considering how physical and digital components affect the p…

cs.CL2021

Modular Networks for Compositional Instruction Following

Rodolfo Corona, Daniel Fried, Coline Devin +2

Standard architectures used in instruction following often struggle on novel compositions of subgoals (e.g. navigating to landmarks or picking up objects) observed during training.…

stat.ML2015

On the accuracy of self-normalized log-linear models

Jacob Andreas, Maxim Rabinovich, Dan Klein +1

Calculation of the log-normalizer is a major computational obstacle in applications of log-linear models with large output spaces. The problem of fast normalizer computation has th…

cs.AI2011

Learning Dependency-Based Compositional Semantics

Percy Liang, Michael I. Jordan, Dan Klein

Suppose we want to build a system that answers a natural language question by representing its semantics as a logical form and computing the answer given a structured database of f…

cs.LG2024

Prompted Contextual Vectors for Spear-Phishing Detection

Daniel Nahmias, Gal Engelberg, Dan Klein +1

Spear-phishing attacks present a significant security challenge, with large language models (LLMs) escalating the threat by generating convincing emails and facilitating target rec…

cs.CL2023

Are Layout-Infused Language Models Robust to Layout Distribution Shifts? A Case Study with Scientific Documents

Catherine Chen, Zejiang Shen, Dan Klein +3

Recent work has shown that infusing layout features into language models (LMs) improves processing of visually-rich documents such as scientific papers. Layout-infused LMs are ofte…

cs.AI2022

Learning Space Partitions for Path Planning

Kevin Yang, Tianjun Zhang, Chris Cummins +6

Path planning, the problem of efficiently discovering high-reward trajectories, often requires optimizing a high-dimensional and multimodal reward function. Popular approaches like…

cs.CL2025

THOUGHTSCULPT: Reasoning with Intermediate Revision and Search

Yizhou Chi, Kevin Yang, Dan Klein

We present THOUGHTSCULPT, a general reasoning and search method for tasks with outputs that can be decomposed into components. THOUGHTSCULPT explores a search tree of potential sol…

cs.CL2021

Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections

Ruiqi Zhong, Kristy Lee, Zheng Zhang +1

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training exam…

cs.CL2021

Constrained Language Models Yield Few-Shot Semantic Parsers

Richard Shin, Christopher H. Lin, Sam Thomson +7

We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural…

cs.CL2017

Fine-Grained Entity Typing with High-Multiplicity Assignments

Maxim Rabinovich, Dan Klein

As entity type systems become richer and more fine-grained, we expect the number of types assigned to a given entity to increase. However, most fine-grained typing work has focused…

cs.AI2025

Why Do Multi-Agent LLM Systems Fail?

Mert Cemri, Melissa Z. Pan, Shuyi Yang +10

Despite enthusiasm for Multi-Agent LLM Systems (MAS), their performance gains on popular benchmarks are often minimal. This gap highlights a critical need for a principled understa…

cs.AI2025

Explaining Datasets in Words: Statistical Models with Natural Language Parameters

Ruiqi Zhong, Heng Wang, Dan Klein +1

To make sense of massive data, we often fit simplified models and then interpret the parameters; for example, we cluster the text embeddings and then interpret the mean parameters…

cs.CL2019

Pragmatically Informative Text Generation

Sheng Shen, Daniel Fried, Jacob Andreas +1

We improve the informativeness of models for conditional text generation using techniques from computational pragmatics. These techniques formulate language production as a game be…

cs.CV2017

Neural Module Networks

Jacob Andreas, Marcus Rohrbach, Trevor Darrell +1

Visual question answering is fundamentally compositional in nature---a question like "where is the dog?" shares substructure with questions like "what color is the dog?" and "where…

eess.AS2020

Digital Voicing of Silent Speech

David Gaddy, Dan Klein

In this paper, we consider the task of digitally voicing silent speech, where silently mouthed words are converted to audible speech based on electromyography (EMG) sensor measurem…

cs.CV2026

Can Language Models Learn to Listen?

Evonne Ng, Sanjay Subramanian, Dan Klein +3

We present a framework for generating appropriate facial responses from a listener in dyadic social interactions based on the speaker's words. Given an input transcription of the s…

cs.CL2024

What Evidence Do Language Models Find Convincing?

Alexander Wan, Eric Wallace, Dan Klein

Retrieval-augmented language models are being increasingly tasked with subjective, contentious, and conflicting queries such as "is aspartame linked to cancer". To resolve these am…

cond-mat.mes-hall2022

Landauer formula for interacting systems: a consistent non-perturbative approximation

Dan Klein, Karen Michaeli

Transport measurements are one of the most widely used methods of characterizing small systems in chemistry and physics. When interactions are negligible, the current through quant…

cs.CL2017

A Minimal Span-Based Neural Constituency Parser

Mitchell Stern, Jacob Andreas, Dan Klein

In this work, we present a minimal neural model for constituency parsing based on independent scoring of labels and spans. We show that this model is not only compatible with class…