
The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP) is being hosted in Budapest, Hungary from October 24th - 29th. We’re excited to share all the work from SAIL that’s being presented, and you’ll find links to papers, videos and blogs below. Feel free to reach out to the contact authors directly to learn more about the work that’s happening at Stanford!
Main Conference
Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICT
Authors: Zikai Zhou, Yufei Jin, Yilin Xu, Yu-Chiang Wang, Chieh-Ju Chao, Monica S. Lam
Contact: zikai@stanford.edu
Links: Paper | Website
Keywords: accountable AI, faithful explanations, neuro-symbolic reasoning, SMT solvers, clinical trial matching
API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces
Authors: Jennifer Wang, Joachim Baumann, Daniel E. Ho, Sanmi Koyejo
Contact: jennjwang@stanford.edu
Links: Paper
Keywords: AI Evaluation, Ecological Validity of Benchmarks, LLM System Audit
Learning Concepts, Not Tokens: Self-Supervised Semantic Alignment for Language Models
Authors: Christine Zhang, Dan Jurafsky, Chen Shani
Contact: chrzhang@stanford.edu
Links: Paper
Keywords: Concept-based Learning, Next Token Prediction, Large Language Models, Semantic Alignment, Concept Supervision, Language Model Training Objectives
Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems
Authors: Aleksandra Urman, Elsa Lichtenegger, Salima Jaoua, Azza Bouleimen, Robin Forsberg, Corinna Hertweck, Stefania Ionescu, Nicolò Pagan, Ancsa Hannak, Joachim Baumann
Contact: urman@ifi.uzh.ch
Links: Paper
Keywords: Cultural bias, T2I, text-to-image generation, prompt revision, multilingual evaluation, stereotyping, cultural representation, benchmark, auditing, multimodal systems
WildSEEK: Evaluating Language Models for Information-Seeking
Authors: Tanise Ceron, Joachim Baumann, Elisa Bassignana, Berat Cabuk, Dirk Hovy, Debora Nozza
Contact: tanise.ceron@unibocconi.it
Links: Paper
Keywords: LLM evaluation, information-seeking, safety, reliability, fairness
We look forward to seeing you at EMNLP 2026!