Christopher Potts

87 papers · 2010–2025 · 12 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (12) 🏃 Academic Marathon (15) 🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (11) 🗺️ Taxonomy Completionist (106) 🏠 Conference Loyalist (31) 🤝 Dynamic Duo (24) 🏆 Keyword Champion 👑 Triple Crown 🔬 Deep Specialist (19) 📈 Trend Setter ⚡ Prolific Year (7) 🗃️ Keyword Collector (271) 🔥 Unstoppable (8) 💎 Century Club (87) ❓ The Questioner (2)

Conferences

EMNLP (31) ACL (16) NAACL (12) NIPS (8) ICLR (7) ICML (4) IJCNLP (4) CLEAR (1) COLING (1) CONLL (1) EACL (1) JMLR (1)

Top co-authors

Atticus Geiger (24) Zhengxuan Wu (18) Omar Khattab (9) Elisa Kreiss (9) Jing Huang (9) Christopher D. Manning (9) Noah Goodman (8) Thomas Icard (7) Matei Zaharia (7) Dan Jurafsky (7)

Research topics

Linguistics (1) Privacy (1)

Keywords

language model (14) large language model (9) natural language inference (8) causal abstraction (7) causal inference (6) text classification (6) representation learning (5) information retrieval (5) natural language processing (5) sentiment analysis (4) transfer learning (4) neural network (4) image captioning (4) benchmark evaluation (4) named entity recognition (3) domain adaptation (3) text generation (3) knowledge distillation (3) retrieval augmented generation (2) visual question answering (2)

Papers

Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors ICML 2025

False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models EMNLP 2025

Improving Pretraining Data Using Perplexity Correlations ICLR 2025

MrT5: Dynamic Token Merging for Efficient Byte-level Language Models ICLR 2025

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks ICLR 2025

Causal Interventions Reveal Shared Structure Across English Filler–Gap Constructions EMNLP 2025

Distinguishing fair from unfair compositional generalization tasks EMNLP 2025

Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability JMLR 2025

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders ICML 2025

Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations EMNLP 2024

Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs EMNLP 2024

Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together EMNLP 2024

MoEUT: Mixture-of-Experts Universal Transformers NIPS 2024

ReFT: Representation Finetuning for Language Models NIPS 2024

ContextRef: Evaluating Referenceless Metrics for Image Description Generation ICLR 2024

ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems NAACL 2024

I am a Strange Dataset: Metalinguistic Tests for Language Models ACL 2024

CausalGym: Benchmarking causal interpretability methods on linguistic tasks ACL 2024

Mission: Impossible Language Models ACL 2024

Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations CLEAR 2024

GIO: Gradient Information Optimization for Training Dataset Selection ICLR 2024

DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines ICLR 2024

MSCAW-coref: Multilingual, Singleton and Conjunction-Aware Word-Level Coreference Resolution EMNLP 2024

AmazonQAC: A Large-Scale, Naturalistic Query Autocomplete Dataset EMNLP 2024

Retrieval Augmented Spelling Correction for E-Commerce Applications EMNLP 2024

Updating CLIP to Prefer Descriptions Over Captions EMNLP 2024

CommVQA: Situating Visual Question Answering in Communicative Contexts EMNLP 2024

Demystifying Verbatim Memorization in Large Language Models EMNLP 2024

pyvene: A Library for Understanding and Improving PyTorch Models via Interventions NAACL 2024

RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations ACL 2024

Detecting Contradictory COVID-19 Drug Efficacy Claims from Biomedical Literature ACL 2023

ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning ACL 2023

Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking ACL 2023

Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training ACL 2023

CAW-coref: Conjunction-Aware Word-level Coreference Resolution EMNLP 2023

Rigorously Assessing Natural Language Explanations of Neurons EMNLP 2023

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca NIPS 2023

Multi-teacher Distillation for Multilingual Spelling Correction EMNLP 2023

UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers EMNLP 2023

BioDEX: Large-Scale Biomedical Adverse Drug Event Extraction for Real-World Pharmacovigilance EMNLP 2023

MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions EMNLP 2023

Lexical Semantics with Large Language Models: A Case Study of English “break” EACL 2023

Causal Proxy Models for Concept-based Model Explanations ICML 2023

Inducing Causal Structure for Interpretable Neural Networks ICML 2022

CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior NIPS 2022

Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models ACL 2022

Concadia: Towards Image-Based Text Generation with a Purpose EMNLP 2022

Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics EMNLP 2022

Systematicity in GPT-3’s Interpretation of Novel English Noun Compounds EMNLP 2022

Hindsight: Posterior-guided training of retrievers for improved open-ended generation ICLR 2022

ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction NAACL 2022

Causal Distillation for Language Models NAACL 2022

Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking NIPS 2021

Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP NIPS 2021

Dynabench: Rethinking Benchmarking in NLP NAACL 2021

Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval NIPS 2021

DynaSent: A Dynamic Benchmark for Sentiment Analysis IJCNLP 2021

Causal Abstractions of Neural Networks NIPS 2021

DynaSent: A Dynamic Benchmark for Sentiment Analysis ACL 2021

Data and Representation for Turkish Natural Language Inference EMNLP 2020

Modeling Subjective Assessments of Guilt in Newspaper Crime Narratives CONLL 2020

Modeling Subjective Assessments of Guilt in Newspaper Crime Narratives EMNLP 2020

Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation EMNLP 2020

Pragmatic Issue-Sensitive Image Captioning EMNLP 2020

Recursive Routing Networks: Learning to Compose Modules for Language Understanding NAACL 2019

TalkDown: A Corpus for Condescension Detection in Context IJCNLP 2019

Posing Fair Generalization Tasks for Natural Language Inference IJCNLP 2019

Effective Feature Representation for Clinical Text Concept Extraction NAACL 2019

Posing Fair Generalization Tasks for Natural Language Inference EMNLP 2019

TalkDown: A Corpus for Condescension Detection in Context EMNLP 2019

Generating Bilingual Pragmatic Color References NAACL 2018

Mittens: an Extension of GloVe for Learning Domain-Specialized Representations NAACL 2018

Pragmatically Informative Image Captioning with Character-Level Inference NAACL 2018

Retrofitting Distributional Embeddings to Knowledge Graphs with Functional Relations COLING 2018

Representing Social Media Users for Sarcasm Detection EMNLP 2018

Learning to Generate Compositional Color Descriptions EMNLP 2016

A Fast Unified Model for Parsing and Sentence Understanding ACL 2016

Text to 3D Scene Generation with Rich Lexical Grounding ACL 2015

A large annotated corpus for learning natural language inference EMNLP 2015

Text to 3D Scene Generation with Rich Lexical Grounding IJCNLP 2015

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank EMNLP 2013

The Life and Death of Discourse Entities: Identifying Singleton Mentions NAACL 2013

Implicatures and Nested Beliefs in Approximate Decentralized-POMDPs ACL 2013

Emergence of Gricean Maxims from Multi-Agent Decision Theory NAACL 2013

A computational approach to politeness with application to social factors ACL 2013

Learning Word Vectors for Sentiment Analysis ACL 2011

“Was It Good? It Was Provocative.” Learning the Meaning of Scalar Adjectives ACL 2010