---

1. Mortality Research With Artificial Intelligence Tools: Applying Language Models to the National Violent Death Reporting System Suicide Narratives, 2003-2023.
   American Journal of Public Health2026-08-06S2
2. Token Rankings are Unforgeable Language Model Signatures
   arXiv.org2026-06-03alphaXiv arXiv S2
3. Side-by-side Comparison Amplifies Dialect Bias in Language Models
   Conference on Fairness, Accountability and Transparency2026-05-23alphaXiv arXiv S2
4. Why Fine-Tuning Encourages Hallucinations and How to Fix It
   arXiv.org2026-04-16alphaXiv arXiv S2
5. Are We Automating the Joy Out of Work? Designing AI to Augment Work, Not Meaning
   International Conference on Human Factors in Computing Systems2026-03-16alphaXiv arXiv S2
6. Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions
   arXiv.org2026-02-27alphaXiv arXiv S2
7. BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity
   2026-02-25alphaXiv arXiv S2
8. Disentangling Geometry, Performance, and Training in Language Models
   arXiv.org2026-02-24alphaXiv arXiv S2
9. BenchBrowser - Collecting Evidence for Evaluating Benchmark Validity
   arXiv.org2026S2
10. ChEmREF: Evaluating Language Model Readiness for Chemical Emergency Response
    arXiv.org2025-11-13alphaXiv arXiv S2
11. Every Language Model Has a Forgery-Resistant Signature
    arXiv.org2025-10-15alphaXiv arXiv S2
12. How Reliable is Language Model Micro-Benchmarking?
    arXiv.org2025-10-09alphaXiv arXiv S2
13. Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs
    arXiv.org2025-10-03alphaXiv arXiv S2
14. Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations
    Annual Meeting of the Association for Computational Linguistics2025-09-30alphaXiv arXiv S2
15. Uncovering Intervention Opportunities for Suicide Prevention with Language Model Assistants
    Annual Meeting of the Association for Computational Linguistics2025-08-25alphaXiv arXiv S2
16. Better Language Model Inversion by Compactly Representing Next-Token Distributions
    Advances in Neural Information Processing Systems 382025-06-20alphaXiv arXiv S2
17. ELI-Why: Evaluating the Pedagogical Utility of Language Model Explanations
    Annual Meeting of the Association for Computational Linguistics2025-06-17alphaXiv arXiv S2
18. Teaching Models to Understand (but not Generate) High-risk Data
    arXiv.org2025-05-05alphaXiv arXiv S2
19. Improving Language Model Personas via Rationalization with Psychological Scaffolds
    Conference on Empirical Methods in Natural Language Processing2025-04-25alphaXiv arXiv S2
20. Evaluating Evaluation Metrics - The Mirage of Hallucination Detection
    Conference on Empirical Methods in Natural Language Processing2025-04-25alphaXiv arXiv S2
21. Evaluation Under Imperfect Benchmarks and Ratings: A Case Study in Text Simplification
    arXiv.org2025-04-13alphaXiv arXiv S2
22. Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge
    Annual Meeting of the Association for Computational Linguistics2025-03-06alphaXiv arXiv S2
23. On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
    arXiv.org2025-02-20alphaXiv arXiv S2
24. Improving LLM Personas via Rationalization with Psychological Scaffolds
    arXiv.org2025S2
25. Political-LLM: Large Language Models in Political Science
    arXiv.org2024-12-09alphaXiv arXiv S2
26. Generating Function Names to Improve Comprehension of Synthesized Programs
    IEEE Symposium on Visual Languages / Human-Centric Computing Languages and Environments2024-09-02S2
27. Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?
    arXiv.org2024-08-26alphaXiv arXiv S2