🧑‍🔬 Erik Jones

🏛️ Affiliations

🏢Constellation TechnologyLargo · United States2026 · 1 papercurrent🎓University of California, BerkeleyBerkeley · United States2023–2025 · 6 papers🎓Stanford UniversityStanford · United States2018–2020 · 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Orca 2: Teaching Small Language Models How to Reason (2023 · 162 citations)
   Small language models (below roughly 10B parameters) typically trail frontier LLMs in zero-shot reasoning.
2. Automatically Auditing Large Language Models via Discrete Optimization (2023 · 89 citations)
   Testing language models for harmful or bizarre behavior before release is hard. Such failures can be rare, and people struggle to write the prompts that trigger them. Jones et al. treat auditing as a search problem. The auditor writes a scoring function over a prompt and its greedy completion, then looks for…

All works

12 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Orca 2: Teaching Small Language Models How to ReasonarXiv:2311.11045Arindam Mitra, Luciano Del Corro, Shweti Mahajan, et al.2023 · 162 citations
2. Robust Encodings: A Framework for Combating Adversarial Typos ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetErik Jones et al.2020 · 126 citations
3. Automatically Auditing Large Language Models via Discrete OptimizationarXiv:2303.04381Erik Jones, Anca Dragan, Aditi Raghunathan, et al.2023 · 89 citations
4. Capturing Failures of Large Language Models Via Human Cognitive Biases ↗neural information processing systems · no summary yetErik Jones, Jacob Steinhardt2022 · 82 citations
5. Feedback Loops With Language Models Drive In-Context Reward Hacking ↗arXiv:2402.06627 · no summary yetAlexander Pan et al.2024 · 26 citations
6. Mass-Producing Failures of Multimodal Systems with Language Models ↗neural information processing systems · no summary yetShengbang Tong, Erik Jones, Jacob Steinhardt2023 · 23 citations
7. Selective Classification Can Magnify Disparities Across Groups ↗arXiv (Cornell University) · no summary yetErik Jones et al.2020 · 15 citations
8. Adversaries Can Misuse Combinations of Safe Models ↗arXiv (Cornell University) · no summary yetErik Jones, Anca D. Dragan, Jacob Steinhardt2024 · 5 citations
9. Forecasting Rare Language Model Behaviors ↗arXiv (Cornell University) · no summary yetErik Jones et al.2025 · 3 citations
10. Uncovering Gaps in How Humans and LLMs Interpret Subjective Language ↗arXiv (Cornell University) · no summary yetErik Jones, Arjun Patrawala, Jacob Steinhardt2025 · 1 citation
11. LLM Layers Immediately Correct Each Other ↗neural information processing systems · no summary yetArjun Patrawala et al.2025
12. Task-Agnostic Robust Encodings for Combating Adversarial Typos ↗no summary yetErik Jones et al.2019

🤝 Co-authors here

8 co-authors with a page, the most papers together first.

• Aditi Raghunathan
• Anca Dragan
• Arindam Mitra
• Hamid Palangi
• Jacob Steinhardt
• Kriti Aggarwal
• Luciano Del Corro
• Sahaj Agarwal

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• neural information processing systems ×3
• Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

🔗 Cited by

Papers of our library cite their works 339 times (of the 149,439 papers whose bibliographies we read); 85 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/erik-jones/