Mirac Suzgun
Stanford PhD researcher known for BIG-Bench Hard (BBH), and work on reasoning, self-consistency, and emergent abilities of LLMs.
- Role
- grad-student
- Currently at
- Stanford University
- twitter.com/mirac_suzgun
- GitHub
- github.com/suzgunmirac
- Scholar
- scholar.google.com/citations
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11Cost-of-Pass: An Economic Framework for Evaluating Language Models
arXiv 2025
Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
arXiv 2025
Belief in the Machine: Investigating Epistemological Blind Spots of Language Models
arXiv 2024
Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models
arXiv 2024
Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding
arXiv 2024
Do Language Models Know When They're Hallucinating References?
arXiv 2023
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
arXiv 2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TMLR
Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding
arXiv 2022
Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
ACL
The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications
the-harvard-uspto-patent-dataset-a-large
Eval contributions
1Affiliations
Frequent co-authors
10from 11 papers
James Zou
Dan Jurafsky
Federico Bianchi
Adam Tauman Kalai
Daniel E. Ho
Jason Wei
research-scientist
Luke Melas-Kyriazi
Mert Yuksekgonul
Sebastian Gehrmann
researcher
Stuart M. Shieber