pith. sign in

Arman Cohan

Identifiers

  • name variant Arman Cohan 0.60 · backfill

Papers (36)

  1. Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence? cs.CL · 2026 · author #2
  2. OpenComputer: Verifiable Software Worlds for Computer-Use Agents cs.AI · 2026 · author #7
  3. Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents? cs.CL · 2026 · author #8
  4. Herculean: An Agentic Benchmark for Financial Intelligence cs.AI · 2026 · author #56
  5. Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction cs.LG · 2026 · author #3
  6. Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems cs.CL · 2026 · author #6
  7. Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future cs.CL · 2026 · author #8
  8. Step-level Optimization for Efficient Computer-use Agents cs.AI · 2026 · author #5
  9. Medical thinking with multiple images cs.CV · 2026 · author #10
  10. SciMDR: Advancing Scientific Multimodal Document Reasoning cs.CL · 2026 · author #6
  11. RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation cs.CL · 2026 · author #7
  12. A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning cs.AI · 2026 · author #8
  13. ANCHOR: Branch-Point Data Generation for GUI Agents cs.AI · 2026 · author #4
  14. Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics cs.AI · 2025 · author #4
  15. Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning cs.CL · 2025 · author #5
  16. Advancing AI Research Assistants with Expert-Involved Learning cs.AI · 2025 · author #26
  17. PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving cs.AI · 2025 · author #7
  18. Survey on Evaluation of LLM-based Agents cs.AI · 2025 · author #7
  19. OLMo: Accelerating the Science of Language Models cs.CL · 2024 · author #15
  20. Longformer: The Long-Document Transformer cs.CL · 2020 · author #3
  21. Ontology-Aware Clinical Abstractive Summarization cs.CL · 2019 · author #3
  22. Overcoming low-utility facets for complex answer retrieval cs.IR · 2018 · author #3
  23. RSDD-Time: Temporal Annotation of Self-Reported Mental Health Diagnoses cs.CL · 2018 · author #3
  24. SMHD: A Large-Scale Resource for Exploring Online Language Usage for Multiple Mental Health Conditions cs.CL · 2018 · author #1
  25. Characterizing Question Facets for Complex Answer Retrieval cs.IR · 2018 · author #3
  26. Helping or Hurting? Predicting Changes in Users' Risk of Self-Harm Through Online Community Interactions cs.CL · 2018 · author #3
  27. A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents cs.CL · 2018 · author #1
  28. GU IRLAB at SemEval-2018 Task 7: Tree-LSTMs for Scientific Relation Classification cs.CL · 2018 · author #3
  29. Depression and Self-Harm Risk Assessment in Online Forums cs.CL · 2017 · author #2
  30. Identifying Harm Events in Clinical Care through Medical Narratives cs.CL · 2017 · author #1
  31. Scientific document summarization via citation contextualization and scientific discourse cs.CL · 2017 · author #1
  32. Contextualizing Citations for Scientific Summarization using Word Embeddings and Domain Knowledge cs.CL · 2017 · author #1
  33. Scientific Article Summarization Using Citation-Context and Article's Discourse Structure cs.CL · 2017 · author #1
  34. A Neural Attention Model for Categorizing Patient Safety Events cs.CL · 2017 · author #1
  35. Triaging Content Severity in Online Mental Health Forums cs.CL · 2017 · author #1
  36. Revisiting Summarization Evaluation for Scientific Articles cs.CL · 2016 · author #1

Mentions

  • 2508.19202 #5 · arxiv_oai · confidence 0.70 Arman Cohan
  • 2605.28778 #2 · arxiv_oai · confidence 0.70 Arman Cohan
  • 2503.21821 #7 · arxiv_oai · confidence 0.70 Arman Cohan
  • 2605.19769 #7 · arxiv_oai · confidence 0.70 Arman Cohan
  • 2605.19196 #8 · arxiv_oai · confidence 0.70 Arman Cohan
  • 2402.00838 #15 · arxiv_oai · confidence 0.70 Arman Cohan

Frequent Coauthors