Jackie CK Cheung

Venues

Frequent coauthors

Papers

1. Active Learning with Non-Uniform Costs for African Natural Language Processing
   EACL 2026 ·

   Bonaventure F. P. Dossou

   DBLP profile ↗ORCID search ↗
2. Identifying and Analyzing Performance-Critical Tokens in Large Language Models
   AAAI 2026 ·

   Yu Bai

   DBLP profile ↗ORCID search ↗
3. (RSA)²: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative Language Understanding
   ACL 2025 ·

   Cesare Spinoso Di Piano

   DBLP profile ↗ORCID search ↗
4. Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
   NAACL 2025 ·

   Khaoula Chehbouni

   DBLP profile ↗ORCID search ↗
5. Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation
   EMNLP 2025 ·

   Ziling Cheng

   DBLP profile ↗ORCID search ↗
6. Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog
   EMNLP 2025 ·

   Lautaro Estienne

   DBLP profile ↗ORCID search ↗
7. Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing
   AAAI 2025 ·

   Behzad Shayegh

   DBLP profile ↗ORCID search ↗
8. Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's Characteristics
   ACL 2025 ·

   Lorenzo Jaime Yu Flores

   DBLP profile ↗ORCID search ↗
9. Learning Task-Agnostic Representations through Multi-Teacher Distillation
   NeurIPS 2025 ·

   Philippe Formont

   DBLP profile ↗ORCID search ↗
10. Neither Valid nor Reliable? Investigating the Use of LLMs as Judges
    NeurIPS 2025 ·

    Khaoula Chehbouni

    DBLP profile ↗ORCID search ↗
11. PreSumm: Predicting Summarization Performance Without Summarizing
    ACL 2025 ·

    Steven Koniaev

    DBLP profile ↗ORCID search ↗
12. Rethinking Full Finetuning from Pretraining Checkpoints in Active Learning for African Languages
    ACL 2025 ·

    Bonaventure F. P. Dossou

    DBLP profile ↗ORCID search ↗
13. Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs
    ACL 2025 ·

    Ziling Cheng

    DBLP profile ↗ORCID search ↗
14. Where Did That Come From? Sentence-Level Error-Tolerant Attribution
    EMNLP 2025 ·

    Ori Ernst

    DBLP profile ↗ORCID search ↗
15. CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling
    EMNLP 2024 ·

    Yu Bai

    DBLP profile ↗ORCID search ↗
16. COSMIC: Mutual Information for Task-Agnostic Summarization Evaluation
    ACL 2024 ·

    Maxime Darrin

    DBLP profile ↗ORCID search ↗
17. Challenges to Evaluating the Generalization of Coreference Resolution Models: A Measurement Modeling Perspective
    ACL 2024 ·

    Ian Porada

    DBLP profile ↗ORCID search ↗
18. Do LLMs Build World Representations? Probing Through the Lens of State Abstraction
    NeurIPS 2024 ·

    Zichao Li

    DBLP profile ↗ORCID search ↗
19. ECBD: Evidence-Centered Benchmark Design for NLP
    ACL 2024 ·

    Yu Lu Liu

    DBLP profile ↗ORCID search ↗
20. Ensemble Distillation for Unsupervised Constituency Parsing
    ICLR 2024 ·

    Behzad Shayegh

    DBLP profile ↗ORCID search ↗
21. From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards
    ACL 2024 ·

    Khaoula Chehbouni

    DBLP profile ↗ORCID search ↗
22. GLIMPSE: Pragmatically Informative Multi-Document Summarization for Scholarly Reviews
    ACL 2024 ·

    Maxime Darrin

    DBLP profile ↗ORCID search ↗
23. How Teachers Can Use Large Language Models and Bloom's Taxonomy to Create Educational Quizzes
    AAAI 2024 ·

    Sabina Elkins

    DBLP profile ↗ORCID search ↗
24. Human-Centered Evaluation of Language Technologies
    EMNLP 2024 ·

    Su Lin Blodgett

    DBLP profile ↗ORCID search ↗
25. Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinations
    EMNLP 2024 ·

    Lei Yu

    DBLP profile ↗ORCID search ↗
26. Separately Parameterizing Singleton Detection Improves End-to-end Neural Coreference Resolution
    NAACL 2024 ·

    Xiyuan Zou

    DBLP profile ↗ORCID search ↗
27. Successor Features for Efficient Multi-Subject Controlled Text Generation
    ICML 2024 ·

    Meng Cao

    DBLP profile ↗ORCID search ↗
28. Unsupervised Layer-Wise Score Aggregation for Textual OOD Detection
    AAAI 2024 ·

    Maxime Darrin

    DBLP profile ↗ORCID search ↗
29. When is an Embedding Model More Promising than Another?
    NeurIPS 2024 ·

    Maxime Darrin

    DBLP profile ↗ORCID search ↗