Valentina Pyatkin
Research scientist at Allen Institute for AI; co-leads OLMo and Tülu open-language-model projects; ACL Theme Paper Award winner.
- Role
- research-scientist
- Currently at
- Allen Institute for AI (Ai2)
- twitter.com/valentina__py
- GitHub
- github.com/valentinapy
- Scholar
- scholar.google.com/citations
- Papers
- 22
Cite
Notes
Only stored in your browser.
Authored papers
22RewardBench 2: Advancing Reward Model Evaluation
preprint
Olmo 3
arXiv 2025
IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance
arXiv 2025
Tulu 3: Pushing Frontiers in Open Language Model Post-Training
preprint
2 OLMo 2 Furious
arXiv 2024
OLMo: Accelerating the Science of Language Models
arXiv 2024
RewardBench: Evaluating Reward Models for Language Modeling
arXiv 2024
Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models
arXiv 2024
Superlatives in Context: Modeling the Implicit Semantics of Superlatives
arXiv 2024
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
arXiv 2024
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
arXiv 2024
Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task Design
arXiv 2023
PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
arXiv 2023
Revisiting Sentence Union Generation as a Testbed for Text Consolidation
arXiv 2023
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
arXiv 2023
Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties
arXiv 2023
QASem Parsing: Text-to-text Modeling of QA-based Semantics
arXiv 2022
ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral Situations
arXiv 2022
Just-DREAM-about-it: Figurative Language Understanding with DREAM-FLUTE
arXiv 2022
Asking It All: Generating Contextualized Questions for any Semantic Role
EMNLP 2021 11
The Possible, the Plausible, and the Desirable: Event-Based Modality Detection for Language Processing
ACL 2021 5
QADiscourse -- Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines
arXiv 2020
Affiliations
Frequent co-authors
10from 22 papers
Faeze Brahman
researcher
Hannaneh Hajishirzi
professor
Ido Dagan
Jacob Morrison
research-engineer
Nathan Lambert
researcher
Noah A. Smith
Nouha Dziri
researcher
Yejin Choi
professor
Hamish Ivison
grad-student
Pradeep Dasigi