--- title: "Peter Hase — author profile and papers" description: "Peter Hase, University of North Carolina at Chapel Hill: 3 papers on Elamur Research (2020–2023), h-index 10 — affiliations, topics, co-authors and who…" canonical: "https://research.elamur.ai/free/en/authors/peter-hase/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/peter-hase/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Peter Hase # Peter Hase Peter Hase has 3 papers in our library, in 2020–2023, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/), [Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/); often with [Mohit Bansal](https://md.research.elamur.ai/free/en/authors/mohit-bansal/), [Archiki Prasad](https://md.research.elamur.ai/free/en/authors/archiki-prasad/), [Shiyue Zhang](https://md.research.elamur.ai/free/en/authors/shiyue-zhang/). 3 papers in our library · 2020–2023 [OpenAlex](https://openalex.org/A5013096489) · [**h-index 10**](https://openalex.org/authors/A5013096489) · [34 works](https://openalex.org/works?filter=author.id:A5013096489) · [724 citations](https://openalex.org/works?filter=author.id:A5013096489&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/peter-hase/#papers) · [🔗 403 citations in our library](https://md.research.elamur.ai/free/en/authors/peter-hase/cited-by/) · [5 more in our library without a page yet](#also) · [⭐ Paper Star rank #3027](https://md.research.elamur.ai/free/en/paper-stars/page/31/#star-3027) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Peter+Hase) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Peter+Hase) · [dblp](https://dblp.org/search?q=Peter+Hase) · [ACL Anthology](https://aclanthology.org/search/?q=Peter+Hase) ## Affiliations [🎓**University of North Carolina at Chapel Hill** Chapel Hill · United States 2018–2026 · 24 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-north-carolina-at-chapel-hill/) · [🏢**Philip Morris International** New York · United States 2026 · 1 paper*current*](https://ror.org/005rxfw29) · [🤝**Schmidt Sciences** New York · United States 2026 · 1 paper*current*](https://ror.org/044fk6795) · [🎓**Stanford University** Stanford · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/stanford-university/) · [🏢**Anthropic** San Francisco 2024–2025 · 3 papers](https://md.research.elamur.ai/free/en/companies/anthropic/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed. ## Concepts, shelves and topics Of its works in our library: the number of works on each and its rating among them. 📚 Shelves 7[Computer Science · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Social Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · [Safety Research · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Software · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/software/) 🧭 Topics 3[Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) · [Evaluation & benchmarks · 1 work](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Interpretability · 1 work](https://md.research.elamur.ai/free/en/topics/interpretability/) ## Works by year ### 2020s [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/prasad-2023-grips-gradient-free-edit-based/) · [**2020** 2 papers](https://md.research.elamur.ai/free/en/authors/peter-hase/year/2020/) ## Papers The most cited first (OpenAlex and our library). 1. **[Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://md.research.elamur.ai/free/en/papers/hase-2020-evaluating-explainable-ai-which-algorithmic/)** *(2020 · 309 citations)* Many algorithms claim to make machine learning models interpretable, but there is little evidence that they help people anticipate what a model will do. 2. **[GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models](https://md.research.elamur.ai/free/en/papers/prasad-2023-grips-gradient-free-edit-based/)** *(2023 · 182 citations)* Instructions written for human annotators often work poorly as prompts for large language models. Manual rewriting is slow and subjective, and gradient-based prompt tuning is expensive and impossible for models available only through an API. The authors propose GrIPS (Gradient-free Instructional Prompt Search). It… 3. **[Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?](https://md.research.elamur.ai/free/en/papers/hase-2020-leakage-adjusted-simulatability-can-models/)** *(2020 · 120 citations)* Models trained on datasets that pair labels with free-text human explanations can write their own natural language justifications. ## All works 8 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them. 1. **[Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://md.research.elamur.ai/free/en/papers/hase-2020-evaluating-explainable-ai-which-algorithmic/)**Peter Hase, Mohit Bansal*[Annual Meeting of the Association for…](https://md.research.elamur.ai/free/en/venues/acl/) · 309 citations* 2. **[GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models](https://md.research.elamur.ai/free/en/papers/prasad-2023-grips-gradient-free-edit-based/)**Archiki Prasad, Peter Hase, Xiang Zhou, et al.*[Conference of the European Chapter of the…](https://md.research.elamur.ai/free/en/venues/eacl/) · 182 citations* 3. **[Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?](https://md.research.elamur.ai/free/en/papers/hase-2020-leakage-adjusted-simulatability-can-models/)**Peter Hase, Shiyue Zhang, Harry Xie, et al.*[Findings of the Association for Computational…](https://md.research.elamur.ai/free/en/venues/findings/) · 120 citations* 4. **[Reasoning Models Don't Always Say What They Think](https://arxiv.org/abs/2505.05410) (original ↗)**Yanda Chen et al.*2025 · arXiv:2505.05410 · 95 citations · no summary yet* 5. **[Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs](https://arxiv.org/abs/2111.13654) (original ↗)**Peter Hase et al.*2021 · arXiv:2111.13654 · 58 citations · no summary yet* 6. **[Methods for Measuring, Updating, and Visualizing Factual Beliefs in Language Models](https://aclanthology.org/2023.eacl-main.199/) (original ↗)**Peter Hase et al.*2023 · Proceedings of the 17th Conference of the… · 50 citations · no summary yet* 7. **[The Unreasonable Effectiveness of Easy Training Data for Hard Tasks](https://aclanthology.org/2024.acl-long.378/) (original ↗)**Peter Hase et al.*2024 · Proceedings of the 62nd Annual Meeting of the… · 18 citations · no summary yet* 8. **[Are language models rational? The case of coherence norms and belief revision](https://arxiv.org/abs/2406.03442) (original ↗)**Thomas Hofweber et al.*2024 · arXiv:2406.03442 · 5 citations · no summary yet* ## Co-authors here 4 co-authors with a page, the most papers together first. - [Mohit Bansal](https://md.research.elamur.ai/free/en/authors/mohit-bansal/) ×3 - [Archiki Prasad](https://md.research.elamur.ai/free/en/authors/archiki-prasad/) - [Shiyue Zhang](https://md.research.elamur.ai/free/en/authors/shiyue-zhang/) - [Xiang Zhou](https://md.research.elamur.ai/free/en/authors/xiang-zhou/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Annual Meeting of the Association for Computational…](https://md.research.elamur.ai/free/en/venues/acl/) ×2: [2020](https://md.research.elamur.ai/free/en/venues/acl/2020/) - [Conference of the European Chapter of the Association for…](https://md.research.elamur.ai/free/en/venues/eacl/) ×2: [2023](https://md.research.elamur.ai/free/en/venues/eacl/2023/) - [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/): [2020](https://md.research.elamur.ai/free/en/venues/findings/2020/) ## Cited by Papers of our library cite their works 403 times (of the 141,840 papers whose bibliographies we read); [27 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/peter-hase/cited-by/). Updated 24 October 2026