Excited to share that our paper “Personalizing LLMs Through User Value Profiles” has been accepted to @emnlpmeeting.bsky.social 2026 Main Track! #emnlp2026

1/ How does the modality of input affect context-memory conflicts (when in-context information contradicts a model’s learned knowledge).

In our #EMNLP2026 Findings paper, we observe modality asymmetry and understand why this occurs.

🧵👇

1/🚨 New paper #emnlp2026

Do multilingual #LLMs work in English? It depends on how you ask. In "Lingua Franca or Probing Artifact?", we probe the same hidden states with three latent language identification methods and get different answers. 🧵👇

#interpretability #NLProc

Are claims like *we are helping underserved communities* actually provable and justified?
Our #EMNLP2026 main paper asks:
When does the framing of multilingual and low-resource #NLP become a caricature?
🧵 1/6

Our paper on measuring epistemic diversity in LLMs is accepted to #EMNLP2026!

We find that diversity has improved, though LLM output is much less diverse than Web search, especially for non-English.

Paper: arxiv.org/pdf/2510.04226
Code/data: github.com/dwright37/ll...

#NLProc @copenlu.bsky.social

Our work on assessing how credibly social science papers apply causal research designs was accepted at #EMNLP2026 🎉. A genuinely interdisciplinary collaboration linking #NLProc and policy evaluation expertise between @dh-fbk.bsky.social and @fbk-irvapp.bsky.social. Preprint: arxiv.org/pdf/2608.27049