PPaperPicks

Mrinmaya Sachan

58 papers at tracked venues · 30 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-8787-8681 ↗Homepage ↗

Venues

ACL ×16EMNLP ×13NAACL ×8NeurIPS ×7EACL ×4ICLR ×3ICML ×2AAAI ×1CHI ×1CSCW ×1ECAI ×1IUI ×1

Frequent coauthors

Jingwei Ni
DBLP profile ↗ORCID search ↗
×4
Junling Wang
DBLP profile ↗ORCID search ↗
×3
Andreas Opedal
DBLP profile ↗ORCID search ↗
×3
Zhijing Jin
DBLP profile ↗ORCID search ↗
×3
Vilém Zouhar
DBLP profile ↗ORCID search ↗
×2
Peng Cui
DBLP profile ↗ORCID search ↗
×2
Tianyu Liu
DBLP profile ↗ORCID search ↗
×2
Jiaoda Li
DBLP profile ↗ORCID search ↗
×2
Nico Daheim
DBLP profile ↗ORCID search ↗
×2
Ekaterina Fadeeva
DBLP profile ↗ORCID search ↗
×1
Donya Rooein
DBLP profile ↗ORCID search ↗
×1
Jiarui Liu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Bridging Instead of Replacing Online Coding Communities with AI through Community-Enriched Chatbot Designs CSCW008
    CSCW 2026 ·
    Junling Wang
    DBLP profile ↗ORCID search ↗
  2. Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?
    EACL 2026 ·
    Jingwei Ni
    DBLP profile ↗ORCID search ↗
  3. Early-Exit and Instant Confidence Translation Quality Estimation
    EACL 2026 ·
    Vilém Zouhar
    DBLP profile ↗ORCID search ↗
  4. Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
    ACL 2026 ·
    Jingwei Ni
    DBLP profile ↗ORCID search ↗
  5. Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval-Augmented Generation
    ACL 2026 ·
    Ekaterina Fadeeva
    DBLP profile ↗ORCID search ↗
  6. PATS: Personality-Aware Teaching Strategies with Large Language Model Tutors
    EACL 2026 ·
    Donya Rooein
    DBLP profile ↗ORCID search ↗
  7. PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers in Overleaf
    ACL 2026 ·
    Jiarui Liu
    DBLP profile ↗ORCID search ↗
  8. Tackling the Root of Misinformation by Teaching Laypeople about Logical Fallacies via Socratic Questioning and Critical Argumentation
    ACL 2026 ·
    Minjing Shi
    DBLP profile ↗ORCID search ↗
  9. Test of Time: Rethinking Temporal Signal of Benchmark Contamination
    ACL 2026 ·
    Terry Jingchen Zhang
    DBLP profile ↗ORCID search ↗
  10. ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
    ACL 2026 ·
    Vladislav Smirnov
    DBLP profile ↗ORCID search ↗
  11. Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification
    EACL 2026 ·
    Paul He
    DBLP profile ↗ORCID search ↗
  12. A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs
    EMNLP 2025 ·
    Artem Shelmanov
    DBLP profile ↗ORCID search ↗
  13. AI-Assisted Human Evaluation of Machine Translation
    NAACL 2025 ·
    Vilém Zouhar
    DBLP profile ↗ORCID search ↗
  14. Are Language Models Efficient Reasoners? A Perspective from Logic Programming
    NeurIPS 2025 ·
    Andreas Opedal
    DBLP profile ↗ORCID search ↗
  15. Calibrating Large Language Models with Sample Consistency
    AAAI 2025 ·
    Qing Lyu
    DBLP profile ↗ORCID search ↗
  16. Can Vision-Language Models Solve Visual Math Equations?
    EMNLP 2025 ·
    Monjoy Narayan Choudhury
    DBLP profile ↗ORCID search ↗
  17. Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification
    EMNLP 2025 ·
    Chenfei Xiong
    DBLP profile ↗ORCID search ↗
  18. DIRAS: Efficient LLM Annotation of Document Relevance for Retrieval Augmented Generation
    NAACL 2025 ·
    Jingwei Ni
    DBLP profile ↗ORCID search ↗
  19. Dense SAE Latents Are Features, Not Bugs
    NeurIPS 2025 ·
    Xiaoqing Sun
    DBLP profile ↗ORCID search ↗
  20. Do Vision-Language Models Really Understand Visual Language?
    ICML 2025 ·
    Yifan Hou
    DBLP profile ↗ORCID search ↗
  21. From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning
    EMNLP 2025 ·
    David Dinucu-Jianu
    DBLP profile ↗ORCID search ↗
  22. GPT-4 as a Homework Tutor Can Improve Student Engagement and Learning Outcomes
    ACL 2025 ·
    Alessandro Vanzo
    DBLP profile ↗ORCID search ↗
  23. Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Models
    ACL 2025 ·
    Junling Wang
    DBLP profile ↗ORCID search ↗
  24. Grammar Control in Dialogue Response Generation for Language Learning Chatbots
    NAACL 2025 ·
    Dominik Glandorf
    DBLP profile ↗ORCID search ↗
  25. Improving Large Language Model Safety with Contrastive Representation Learning
    EMNLP 2025 ·
    Samuel Simko
    DBLP profile ↗ORCID search ↗
  26. Investigating the Zone of Proximal Development of Language Models for In-Context Learning
    NAACL 2025 ·
    Peng Cui
    DBLP profile ↗ORCID search ↗
  27. Language Model Alignment in Multilingual Trolley Problems
    ICLR 2025 ·
    Zhijing Jin
    DBLP profile ↗ORCID search ↗
  28. MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs
    ICLR 2025 ·
    Andreas Opedal
    DBLP profile ↗ORCID search ↗
  29. MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors
    EMNLP 2025 ·
    Jakub Macina
    DBLP profile ↗ORCID search ↗
  30. Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing
    NeurIPS 2025 ·
    Yilmazcan Özyurt
    DBLP profile ↗ORCID search ↗
  31. Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation
    NAACL 2025 ·
    Tianyu Liu
    DBLP profile ↗ORCID search ↗
  32. Probing for Arithmetic Errors in Language Models
    EMNLP 2025 ·
    Yucheng Sun
    DBLP profile ↗ORCID search ↗
  33. SIKeD: Self-guided Iterative Knowledge Distillation for Mathematical Reasoning
    ACL 2025 ·
    Shivam Adarsh
    DBLP profile ↗ORCID search ↗
  34. SeePhys: Does Seeing Help Thinking? - Benchmarking Vision-Based Physics Reasoning
    NeurIPS 2025 ·
    Kun Xiang
    DBLP profile ↗ORCID search ↗
  35. The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure
    EMNLP 2025 ·
    Yu Fan
    DBLP profile ↗ORCID search ↗
  36. Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failure
    ACL 2025 ·
    Romain Puech
    DBLP profile ↗ORCID search ↗
  37. A Transformer with Stack Attention
    NAACL 2024 ·
    Jiaoda Li
    DBLP profile ↗ORCID search ↗
  38. AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators
    ACL 2024 ·
    Jingwei Ni
    DBLP profile ↗ORCID search ↗
  39. Book2Dial: Generating Teacher Student Interactions from Textbooks for Cost-Effective Development of Educational Chatbots
    ACL 2024 ·
    Junling Wang
    DBLP profile ↗ORCID search ↗
  40. Can Large Language Models Infer Causation from Correlation?
    ICLR 2024 ·
    Zhijing Jin
    DBLP profile ↗ORCID search ↗
  41. CausalCite: A Causal Formulation of Paper Citations
    ACL 2024 ·
    Ishan Kumar
    DBLP profile ↗ORCID search ↗
  42. Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals
    ACL 2024 ·
    Francesco Ortu
    DBLP profile ↗ORCID search ↗
  43. Confidence Regulation Neurons in Language Models
    NeurIPS 2024 ·
    Alessandro Stolfo
    DBLP profile ↗ORCID search ↗
  44. Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
    NeurIPS 2024 ·
    Giorgio Piatti
    DBLP profile ↗ORCID search ↗
  45. Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis
    EMNLP 2024 ·
    Zhiheng Lyu
    DBLP profile ↗ORCID search ↗
  46. Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?
    ICML 2024 ·
    Andreas Opedal
    DBLP profile ↗ORCID search ↗
  47. Efficiently Computing Susceptibility to Context in Language Models
    EMNLP 2024 ·
    Tianyu Liu
    DBLP profile ↗ORCID search ↗
  48. Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
    NAACL 2024 ·
    Nico Daheim
    DBLP profile ↗ORCID search ↗
  49. How to Engage your Readers? Generating Guiding Questions to Promote Active Reading
    ACL 2024 ·
    Peng Cui
    DBLP profile ↗ORCID search ↗
  50. Implicit Personalization in Language Models: A Systematic Study
    EMNLP 2024 ·
    Zhijing Jin
    DBLP profile ↗ORCID search ↗
  51. On Affine Homotopy between Language Encoders
    NeurIPS 2024 ·
    Robin Chan
    DBLP profile ↗ORCID search ↗
  52. RELIC: Investigating Large Language Model Responses using Self-Consistency
    CHI 2024 ·
    Furui Cheng
    DBLP profile ↗ORCID search ↗
  53. RETRO-LI: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization
    ECAI 2024 ·
    Gentiana Rashiti
    DBLP profile ↗ORCID search ↗
  54. Slicing, Chatting, and Refining: A Concept-Based Approach for Machine Learning Model Validation with ConceptSlicer
    IUI 2024 ·
    Xiaoyu Zhang
    DBLP profile ↗ORCID search ↗
  55. Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
    EMNLP 2024 ·
    Nico Daheim
    DBLP profile ↗ORCID search ↗
  56. The ART of LLM Refinement: Ask, Refine, and Trust
    NAACL 2024 ·
    Kumar Shridhar
    DBLP profile ↗ORCID search ↗
  57. Towards Aligning Language Models with Textual Feedback
    EMNLP 2024 ·
    Saüc Abadal Lloret
    DBLP profile ↗ORCID search ↗
  58. What Do Language Models Learn in Context? The Structured Task Hypothesis
    ACL 2024 ·
    Jiaoda Li
    DBLP profile ↗ORCID search ↗