---

1. string2string Studio: An Interactive, In-Browser Platform for String-to-String Algorithms
   2026-08-04alphaXiv arXiv S2
2. Social calibration of sycophantic AI-Response.
   Science2026-07-16S2
3. You Talkin to Me?: A Network Analysis of Gendered Speaker-Addressee Patterns in Film Screenplays
   2026-06-26alphaXiv arXiv S2
4. Algorithmic Monocultures in Hiring
   Conference on Fairness, Accountability and Transparency2026-05-26alphaXiv arXiv S2
5. Cognitive offloading and the speedup illusion in human-AI interaction
   arXiv.org2026-05-22alphaXiv arXiv S2
6. The efficiency-gain illusion: People underestimate the rate of AI use and overestimate its benefits on simple tasks
   arXiv.org2026-05-21alphaXiv arXiv S2
7. Evaluating Commercial AI Chatbots as News Intermediaries
   arXiv.org2026-05-21alphaXiv arXiv S2
8. PreFT: Prefill-only finetuning for efficient inference
   arXiv.org2026-05-14alphaXiv arXiv S2
9. Verbalizing LLMs' Assumptions About the User to Calibrate Expectations and Reduce Sycophancy
   CHI Extended Abstracts2026-04-13S2
10. Verbalizing LLMs' assumptions to explain and control sycophancy
    arXiv.org2026-04-03alphaXiv arXiv S2
11. Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models
    2026-03-31alphaXiv arXiv S2
12. SumTablets: A Transliteration Dataset of Sumerian Tablets
    ML4AL2026-02-25alphaXiv arXiv S2
13. Beyond Tokens: Concept-Level Training Objectives for LLMs
    Conference of the European Chapter of the Association for Computational Linguistics2026-01-16alphaXiv arXiv S2
14. The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices?
    arXiv.org2026-01-12alphaXiv arXiv S2
15. Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition
    arXiv.org2026-01-11alphaXiv arXiv S2
16. Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs
    Annual Meeting of the Association for Computational Linguistics2026-01-07alphaXiv arXiv S2
17. 🧑‍🍳 Cooking Up Creativity : Enhancing LLM Creativity through Structured Recombination
    Transactions of the Association for Computational Linguistics2026S2
18. Language models cannot reliably distinguish belief from knowledge and fact
    Nature Machine Intelligence2025-11-01S2
19. Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations
    arXiv.org2025-10-14alphaXiv arXiv S2
20. Attention to Non-Adopters
    Annual Meeting of the Association for Computational Linguistics2025-10-10alphaXiv arXiv S2
21. Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models
    Automatic Speech Recognition & Understanding2025-10-02alphaXiv arXiv S2
22. Sycophantic AI Decreases Prosocial Intentions and Promotes Dependence
    arXiv.org2025-10-01alphaXiv arXiv S2
23. Cross-linguistic universality in speech emotion recognition: Comparing multilingual and monolingual computational speech models
    Journal of the Acoustical Society of America2025-10-01S2
24. Artificial intelligence for food innovation
    Nature Food2025-09-25alphaXiv arXiv S2
25. False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models
    Conference on Empirical Methods in Natural Language Processing2025-09-23alphaXiv arXiv S2
26. Racial Disparities in the Discretionary Context of Traffic Stops: How Organizational Practices Shape Institutional Interactions
    Journal of Social Issues2025-09-01S2
27. The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties
    Interspeech2025-08-17alphaXiv arXiv S2
28. Humans overrely on overconfident language models, across languages
    arXiv.org2025-07-08alphaXiv arXiv S2
29. From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
    arXiv.org2025-05-21alphaXiv arXiv S2
30. Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity
    arXiv.org2025-05-21alphaXiv arXiv S2
31. Mechanistic evaluation of Transformers and state space models
    arXiv.org2025-05-21alphaXiv arXiv S2
32. Sycophantic AI decreases prosocial intentions and promotes dependence.
    Science2025-05-20alphaXiv arXiv S2
33. In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties
    Conference on Empirical Methods in Natural Language Processing2025-05-20alphaXiv arXiv S2
34. Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination
    2025-04-29alphaXiv arXiv S2
35. Constructing Datasets From Public Police Body Camera Footage
    IEEE International Conference on Acoustics, Speech, and Signal Processing2025-04-06S2
36. HumT DumT: Measuring and controlling human-like language in LLMs
    Annual Meeting of the Association for Computational Linguistics2025-02-18alphaXiv arXiv S2
37. CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition
    arXiv.org2025-02-03alphaXiv arXiv S2
38. What can large language models do for sustainable food?
    International Conference on Machine Learning2025-02-02alphaXiv arXiv S2
39. AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
    International Conference on Machine Learning2025-01-28alphaXiv arXiv S2
40. Cooking Up Creativity: A Cognitively-Inspired Approach for Enhancing LLM Creativity through Structured Representations
    arXiv.org2025S2
41. REL-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance
    North American Chapter of the Association for Computational Linguistics2025S2
42. Soft production preferences emerge from a bottleneck on memory
    Annual Meeting of the Cognitive Science Society2025S2
43. Belief in the Machine: Investigating Epistemological Blind Spots of Language Models
    arXiv.org2024-10-28alphaXiv arXiv S2
44. Bayesian scaling laws for in-context learning
    arXiv.org2024-10-21alphaXiv arXiv S2
45. Coming into relations: How communication reveals and persuades relational decisions
    Soc. Networks2024-10-01S2
46. People who share encounters with racism are silenced online by humans and machines, but a guideline-reframing intervention holds promise
    Proceedings of the National Academy of Sciences of the United States of America2024-09-09S2
47. Leveraging body-worn camera footage to assess the effects of training on officer communication during traffic stops
    PNAS Nexus2024-09-01S2
48. AI generates covertly racist decisions about people based on their dialect
    Nature2024-08-28S2
49. Can Unconfident LLM Annotations Be Used for Confident Conclusions?
    North American Chapter of the Association for Computational Linguistics2024-08-27alphaXiv arXiv S2
50. A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech models
    Interspeech2024-08-24alphaXiv arXiv S2
51. Model Alignment as Prospect Theoretic Optimization
    International Conference on Machine Learning2024S2
52. Bayesian Prompt Ensembles: Model Uncertainty Estimation for Black-Box Large Language Models
    Annual Meeting of the Association for Computational Linguistics2024S2
53. Ask Again, Then Fail: Large Language Models’ Vacillations in Judgment
    Volume 12024S2
54. Navigating the Grey Area: Expressions of Overconfidence and Uncertainty in Language Models
    arXiv.org2023S2
55. Multilingual BERT has an Accent: Evaluating English Influences on Fluency in Multilingual Models
    SIGTYP2023S2
56. Mini But Mighty: Efficient Multilingual Pretraining with Linguistically-Informed Data Selection
    Findings2023S2
57. When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization
    Conference of the European Chapter of the Association for Computational Linguistics2023S2
58. Upper-bound Translation Performance of Llama-2 Under Idealized Setup
    S2
59. Speech and Language Processing. Dependency Parsing
    S2
60. Speech and Language Processing: an Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. 8 Speech Synthesis
    S2
61. Speech and Language Processing. Part-of-speech Tagging
    S2
62. VERY EARLY DRAFT The Beginner ' s Guide to the ICSI Speech Software
    S2
63. Speech and Language Processing. Hidden Markov Models
    S2
64. Speech and Language Processing. Chapter 7 Logistic Regression
    S2
65. Demographic Stereotypes in Text-to-Image Generation
    S2
66. Lesson learned on how to develop and deploy light-weight models in the era of humongous Language Models
    S2
67. LLM Alignment via Reinforcement Learning from Multi-role Debates as Feedback
    S2
68. OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes
    S2
69. On Gender Differences in the Distribution of um and uh
    S2
70. Do You Smile with Your Nose? Stylistic Variation in Twitter Emoticons
    S2
71. Proceedings of the Annual Meeting of the Cognitive Science Society
    S2