Greg Durrett

Associate Professor@New York University·美国·OpenReview

研究方向

question answering · automated reasoning · natural language inference · interpretability in NLP · text generation · text summarization · large language models · pre-training

Greg Durrett

OpenThoughts: Data Recipes for Reasoning Models

SkillFactory: Self-Distillation for Learning Cognitive Behaviors

Propagating Knowledge in LLMs with Hypernetworks

Learning Composable Chains-of-Thought

Adaptive Margin RLHF via Preference over Preferences

CRUST-Bench: A Comprehensive Benchmark for C-to-safe-Rust Transpilation

LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation

Sparta Alignment: Collectively Aligning Multiple Language Models through Combat

QUDsim: Quantifying Discourse Similarities in LLM-Generated Text

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Understanding Synthetic Context Extension via Retrieval Heads

EvalAgents: Discovering Implicit Evaluation Criteria from the Web

Understanding Synthetic Context Extension via Retrieval Heads

RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models

CodeUpdateArena: Benchmarking Knowledge Editing on API Updates

Proof Search Augmented Language Models

Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation

PropMEND: Hypernetworks for Knowledge Propagation in LLMs