Oyvind Tafjord

35 papers · 2016–2025 · 9 conferences · across top CS/AI conferences

Achievements

🏃 Academic Marathon (9) 🐝 Cross-Pollinator (12) 🗺️ Taxonomy Completionist (57) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (8) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (9) 👥 Mega-Team (43) 🏆 Grand Slam 🤝 Dynamic Duo (23) 🌱 Topic Pioneer 🔬 Deep Specialist (10) 🧬 Topic Evolution 🏆 Keyword Champion (3) 📈 Trend Setter 🗃️ Keyword Collector (151) 🔥 Unstoppable (8) 🚀 Conference Pioneer 💎 Century Club (35) ⚡ Prolific Year (5)

Conferences

EMNLP (14) ACL (7) NIPS (4) ICLR (3) AAAI (2) IJCNLP (2) ICML (1) IJCAI (1) NAACL (1)

Top co-authors

Peter Clark (23) Hannaneh Hajishirzi (7) Bhavana Dalvi Mishra (6) Ashish Sabharwal (6) Jesse Dodge (5) Kyle Richardson (5) Dirk Groeneveld (5) Matt Gardner (5) Akshita Bhagia (5) Peter Jansen (5)

Research topics

Digital Humanities (1)

Keywords

question answering (11) language model (7) natural language inference (4) benchmark dataset (4) pre-trained language model (4) large language model (4) qualitative reasoning (3) reading comprehension (3) natural language understanding (3) pretrained language model (3) neural network (2) multiple-choice question (2) agent system (2) entailment tree (2) textual entailment (2) semantic analysis (2) language modeling (2) natural language processing (2) text generation (2) in-context learning (1)

Papers

From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question-Answering ICLR 2025

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions ICLR 2025

OLMES: A Standard for Language Model Evaluations NAACL 2025

DataDecide: How to Predict Best Pretraining Data with Small Experiments ICML 2025

CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation ACL 2025

OLMoE: Open Mixture-of-Experts Language Models ICLR 2025

OLMo: Accelerating the Science of Language Models ACL 2024

Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research ACL 2024

Paloma: A Benchmark for Evaluating Language Model Fit NIPS 2024

DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents NIPS 2024

Digital Socrates: Evaluating LLMs through Explanation Critiques ACL 2024

Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic EMNLP 2024

Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracy EMNLP 2023

Language Models with Rationality EMNLP 2023

LILA: A Unified Benchmark for Mathematical Reasoning EMNLP 2022

Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering NIPS 2022

Entailer: Answering Questions with Faithful and Truthful Chains of Reasoning EMNLP 2022

Towards Teachable Reasoning Systems: Using a Dynamic Memory of User Feedback for Continual System Improvement EMNLP 2022

Explaining Answers with Entailment Trees EMNLP 2021

BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief EMNLP 2021

“Let Your Characters Tell Their Story”: A Dataset for Character-Centric Narrative Understanding EMNLP 2021

ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language ACL 2021

ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language IJCNLP 2021

UNIFIEDQA: Crossing Format Boundaries with a Single QA System EMNLP 2020

SUPP.AI: finding evidence for supplement-drug interactions ACL 2020

“You are grounded!”: Latent Name Artifacts in Pre-trained Language Models EMNLP 2020

Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge NIPS 2020

Transformers as Soft Reasoners over Language IJCAI 2020

Declarative Question Answering over Knowledge Bases Containing Natural Language Text with Answer Set Programming AAAI 2019

QUAREL: A Dataset and Models for Answering Questions about Qualitative Relationships AAAI 2019

Reasoning Over Paragraph Effects in Situations EMNLP 2019

QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions EMNLP 2019

QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions IJCNLP 2019

AllenNLP: A Deep Semantic Natural Language Processing Platform ACL 2018

Semantic Parsing to Probabilistic Programs for Situated Question Answering EMNLP 2016