Hello! I am a fifth-year PhD student at UC Berkeley working on machine learning, NLP, and computer security. I am advised by Dan Klein and Dawn Song, and I also work with external collaborators such as Sameer Singh, Nicholas Carlini, and Colin Raffel. My research is supported by the Apple Scholars in AI Fellowship. Outside of Berkeley, I have interned at Google Brain, FAIR, and AI2.

I'm on the job market for academia and industry!

Hello! I am a fifth-year PhD student at UC Berkeley working on NLP, machine learning, and computer security. I am advised by Dan Klein and Dawn Song, and I also work with external collaborators such as Sameer Singh, Nicholas Carlini, and Colin Raffel. My research is supported by the Apple Scholars in AI Fellowship. Outside of Berkeley, I have interned at Google Brain, FAIR, and AI2.

I'm on the job market for academia and industry!

Current Research Interests

My research focuses on enhancing the security/privacy/robustness of ML, improving large language models, and the intersection of these topics. Some of my recent work includes:

• Memorization & Privacy We've shown that LMs and diffusion models can memorize their training data [1,2,3,4], raising concerns regarding privacy, copyright agreements, GDPR statutes, and more.
• Prompting & Decoding We've done some of the early work on prompting LMs, including prompt design [4,5], parameter efficiency [6], and understanding failure modes [7].
• Robustness We've studied natural [8] and adversarial distribution shifts [9,10,11], and we have traced model errors back to quality and diversity issues in the training data [12,13,14,15].
• New Threat Models We've explored and refined new types of adversarial vulnerabilities, including stealing models weights [16,17] and poisoning training sets [18,19].

Selected Publications

Here are a few of my representative papers. See my Google Scholar page for a complete list.

• 

  The False Promise of Imitating Proprietary LLMs

  Arnav Gudibande*, Eric Wallace*, Charlie Snell*, Xinyang Geng, Hao Liu, Pieter Abbeel, Sergey Levine, Dawn Song

  arXiv 2023

  TLDR | Twitter #1#2#3| Paper| Code| Citation

  ---

  TLDR: We critically analyze the emerging trend of training open-source LMs to imitate predictions from proprietary LLMs (e.g., Alpaca, Koala, Vicuna).
  

  @article{gudibande2023false,
      title={The False Promise of Imitating Proprietary {LLMs}},
      author={Gudibande, Arnav and Wallace, Eric and Snell, Charlie and Geng, Xinyang and Liu, Hao and Abbeel, Pieter and Levine, Sergey and Song, Dawn},
      journal={arXiv preprint arXiv:2305.15717},
      year={2023}}

• 

  Extracting Training Data from Diffusion Models

  Nicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramèr, Borja Balle, Daphne Ippolito, Eric Wallace

  USENIX 2023

  TLDR | Twitter| Paper| Citation

  ---

  TLDR: We show how to extract hundreds of memorized images from popular diffusion models like Imagen and Stable Diffusion.
  

  @inproceedings{carlini2023extracting,
            title={Extracting training data from diffusion models},
            author={Carlini, Nicholas and Hayes, Jamie and Nasr, Milad and Jagielski, Matthew and Sehwag, Vikash and Tram{\`e}r, Florian and Balle, Borja and Ippolito, Daphne and Wallace, Eric},
            booktitle={USENIX Security Symposium},
            year={2023}}

• 

  Poisoning Language Models During Instruction Tuning

  Alexander Wan*, Eric Wallace*, Sheng Shen, Dan Klein

  ICML 2023

  TLDR | Twitter| Paper| Code| Poster| Citation

  ---

  TLDR: We show that adversaries can poison training sets to manipulate LLM predictions whenever a desired trigger phrase appears, regardless of the task.
  

  @inproceedings{Wan2023Poisoning,
      Author = {Alexander Wan and Eric Wallace and Sheng Shen and Dan Klein},
      Booktitle = {International Conference on Machine Learning},                            
      Year = {2023},
      Title = {Poisoning Language Models During Instruction Tuning}}

• 

  Automated Crossword Solving

  Eric Wallace*, Nicholas Tomlin*, Albert Xu*, Kevin Yang*, Eshaan Pathak*, Matt Ginsberg, Dan Klein

  ACL 2022. First Superhuman Crossword AI

  TLDR| Blog| Demo| Twitter| Paper| Code| Slides| Poster| Citation

  ---

  TLDR: We create an AI for solving crossword puzzles that outperforms the world's best human players.
  

  @inproceedings{Wallace2022Crosswords,  
      title={Automated Crossword Solving},
      author={Wallace, Eric and Tomlin, Nicholas and Xu, Albert and Yang, Kevin and Pathak, Eshaan and Ginsberg, Matthew L. and Klein, Dan}, 
      booktitle={Association for Computational Linguistics},
      year={2022}}

• 

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

  Tony Zhao*, Eric Wallace*, Shi Feng, Dan Klein, Sameer Singh

  ICML 2021. Oral Presentation, top 3%

  TLDR| Twitter #1#2| Paper| Code| Slides| Citation

  ---

  TLDR: We are the first to show that LLM accuracy highly varies across different prompts. We propose a calibration procedure that mitigates the need for prompt engineering.
  

  @inproceedings{Zhao2021Calibrate,  
            Title = {Calibrate Before Use: Improving Few-shot Performance of Language Models},
            Author = {Tony Z. Zhao and Eric Wallace and Shi Feng and Dan Klein and Sameer Singh}, 
            booktitle={International Conference on Machine Learning},
            Year = {2021}}

• 

  Extracting Training Data From Large Language Models

  Nicholas Carlini, Florian Tramèr, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Úlfar Erlingsson, Alina Oprea, Colin Raffel

  USENIX Security 2021. PET Award Runner Up

  TLDR| Blog| Twitter #1#2| Paper| Code| Citation

  ---

  TLDR: We create a method for extracting verbatim training examples from an LLM.
  

  @inproceedings{carlini2020extracting,
              title={Extracting Training Data from Large Language Models},
              author={Nicholas Carlini and Florian Tram\`er and Eric Wallace and Matthew Jagielski 
               and Ariel Herbert-Voss and Katherine Lee and Adam Roberts and Tom Brown
               and Dawn Song and \'Ulfar Erlingsson and Alina Oprea and Colin Raffel},
              booktitle={USENIX Security Symposium},
              year={2021}}

• 

  AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

  Taylor Shin*, Yasaman Razeghi*, Robert L Logan IV*, Eric Wallace, Sameer Singh

  EMNLP 2020

  TLDR| Twitter| Paper| Code| Citation

  ---

  TLDR: We propose a method for automatically designing prompts for LLMs.
  

  @inproceedings{Shin2020Autoprompt,
            Author = {Taylor Shin and Yasaman Razeghi and Robert L. Logan IV and Eric Wallace and Sameer Singh},    
            BookTitle={Empirical Methods in Natural Language Processing},
            Year = {2020},
            Title = {{AutoPrompt}: Eliciting Knowledge from Language Models with Automatically Generated Prompts}}

• 

  Universal Adversarial Triggers for Attacking and Analyzing NLP

  Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, Sameer Singh

  EMNLP 2019

  TLDR| Video| Blog| Twitter| Paper| Code| Slides| Citation

  ---

  TLDR: We create phrases that cause a model to produce a specific prediction when concatenated to any input. Triggers reveal egregious and insightful errors for text classification, reading comprehension, and text generation.
  

  @inproceedings{Wallace2019Triggers,
      Author = {Eric Wallace and Shi Feng and Nikhil Kandpal and Matt Gardner and Sameer Singh},
      Booktitle = {Empirical Methods in Natural Language Processing},
      Year = {2019},
      Title = {Universal Adversarial Triggers for Attacking and Analyzing {NLP}}}

• 

  AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models

  Eric Wallace, Jens Tuyls, Junlin Wang, Sanjay Subramanian, Matt Gardner, Sameer Singh

  EMNLP 2019. Best Demo Award

  TLDR| Landing Page| Twitter| Demo| Paper| Poster| Citation

  ---

  TLDR: We build an open-source toolkit on top of AllenNLP that makes it easy to interpret NLP models.
  

  @inproceedings{Wallace2019AllenNLP,
                       Author = {Eric Wallace and Jens Tuyls and Junlin Wang and Sanjay Subramanian and Matt Gardner and Sameer Singh},
                       Booktitle = {Empirical Methods in Natural Language Processing},
                       Year = {2019},
                       Title = {{AllenNLP Interpret}: A Framework for Explaining Predictions of {NLP} Models}}

Teaching & Mentoring

I enjoy teaching and mentoring students. I advise undergraduate students on research projects (feel free to email me), and I have been involved with multiple courses here at Berkeley.

• 

  CS294: Responsible Generative AI

  UC Berkeley, Fall 2023

  This is a brand new seminar course at the intersection of LLMs and topics such as privacy, safety, ethics, and decentralization.

  Materials

• 

  CS188: Intro to AI

  UC Berkeley, Summer 2023

  I was a graduate student instructor for Berkeley's Intro to AI course. This class is a great place to get up to speed on AI fundamentals (e.g., search, probability, inference).

  Materials

• 

  CS288: Natural Language Processing

  UC Berkeley, Spring 2023

  I was a co-instructor alongside Dan Klein and Kevin Lin for Berkeley's NLP course. In the second half of the course, I covered cutting-edge topics such as LLM scaling, risks, RLHF, and more.

  Materials

• 

  Interpreting Predictions of NLP Models

  EMNLP 2020

  Sameer Singh, Matt Gardner, and I gave a tutorial on methods for interpreting and explaining the predictions of NLP models at NLP.

  Slides| Website

Selected Media Coverage

Here are a few articles that feature my work, including interviews with my colleagues or myself.

• What a Crossword AI Reveals About Humans

• Privacy & Security for Diffusion and LMs

• What does GPT-3 “know” about me?

• Neil deGrasse Tyson Podcast (Crosswords)

• Does GPT-2 Know Your Phone Number?

• AI models spit out photos of people and copyrighted images

• Privacy Considerations in Language Models

• Neural Crossword Solver Outperforms Humans For First Time