Christopher Potts
- Papers
- 37
Cite
Notes
Only stored in your browser.
Authored papers
37HyperSteer: Activation Steering at Scale with Hypernetworks
arXiv 2025
WARP: An Efficient Engine for Multi-Vector Retrieval
arXiv 2025
Do Language Models Use Their Depth Efficiently?
arXiv 2025
Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors
arXiv 2025
Structured Prompting Enables More Robust Evaluation of Language Models
arXiv 2025
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
arXiv 2025
Multi-module GRPO: Composing Policy Gradients and Prompt Optimization for Language Model Programs
arXiv 2025
Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
arXiv 2024
CausalGym: Benchmarking causal interpretability methods on linguistic tasks
arXiv 2024
MoEUT: Mixture-of-Experts Universal Transformers
arXiv 2024
RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations
arXiv 2024
Mission: Impossible Language Models
arXiv 2024
MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
arXiv 2024
I am a Strange Dataset: Metalinguistic Tests for Language Models
arXiv 2024
Improving Pretraining Data Using Perplexity Correlations
arXiv 2024
ReFT: Representation Finetuning for Language Models
arXiv 2024
pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
arXiv 2024
In-Context Learning for Extreme Multi-Label Classification
arXiv 2024
Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
arXiv 2024
Building Efficient and Effective OpenQA Systems for Low-Resource Languages
arXiv 2024
A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
arXiv 2024
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
arXiv 2023
UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers
arXiv 2023
ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems
arXiv 2023
GIO: Gradient Information Optimization for Training Dataset Selection
arXiv 2023
ContextRef: Evaluating Referenceless Metrics For Image Description Generation
arXiv 2023
ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning
arXiv 2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
arXiv 2022
PLAID: An Efficient Engine for Late Interaction Retrieval
arXiv 2022
Psychologically-informed chain-of-thought prompts for metaphor understanding in large language models
arXiv 2022
Causal Proxy Models for Concept-Based Model Explanations
arXiv 2022
Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics
arXiv 2022
Data and Representation for Turkish Natural Language Inference
EMNLP 2020 11
DynaSent: A Dynamic Benchmark for Sentiment Analysis
ACL 2021 5
Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation
EMNLP (BlackboxNLP) 2020 11
A large annotated corpus for learning natural language inference
a-large-annotated-corpus-for-learning-natural-1
Affiliations
Frequent co-authors
10from 37 papers
Atticus Geiger
Christopher D. Manning
Omar Khattab
Zhengxuan Wu
Matei Zaharia
founder
Aryaman Arora
Jing Huang
Karel D'Oosterlinck
Róbert Csordás
Dilara Soylu
grad-student