Our papers for #emnlp2026
See you in Budapest!
#nlproc @seanpapay.bsky.social @mikolajgolecki.bsky.social
@bamnlp.de
@bamnlp.deOur papers for #emnlp2026
See you in Budapest!
#nlproc @seanpapay.bsky.social @mikolajgolecki.bsky.social
@markar.bsky.socialAnyone going to #EMNLP2026? Please consider helping us understand how people use machine translation tools when abroad!
(and if you can't, please share!)
@sfu-cs-ai.bsky.socialEMNLP 2026 is coming up soon and we will be there! See you in Budapest đź‡đź‡ş Oct 24–29 #EMNLP2026
Check out our work!
@textandlanguagelab.bsky.socialOur new research paper by Katrin Rohrbacher @katrohrbacher.bsky.social, Björn Nieth, Emmanuelle Salin , Bjoern Eskofier, and Michaela Mahlberg @michamahlberg.bsky.social, in a nutshell, accepted at #EMNLP2026
Read the full paper here: arxiv.org/pdf/2609.02482
@emnlpmeeting.bsky.social📢 EMNLP 2026 invites applications to organize Birds-of-a-Feather sessions and Affinity Group meetings.
🗓️ Deadline: Oct 2 (AoE)
đź”— 2026.emnlp.org/calls/bof/
@ruggsea.eurosky.socialCurrently registering for #EMNLP2026 next month in Budapest!
Is anybody else that follows me going?
Btw thanks to @eugenevinitsky.bsky.social for making a conference page for it on lea.ac!
@eranhirsch.bsky.socialIn deep research reports, many sentences aren't supported by their citations: recall is 58.7% in NVIDIA AI-Q and 7.1% in TrajectoryKit.
Our #EMNLP2026 paper (main conf) proposes an algorithm that traces each error to the agent that introduced it, and identifies the error type.
@emnlpmeeting.bsky.socialThe Early Registration deadline for #EMNLP2026 is September 24. Only 2 days left!
@shroom-st.bsky.socialExcited to share that our overview paper is accepted to #UncertaiNLP workshop! We will present it on October 29th @emnlpmeeting.bsky.social
@dig-telecom-paris.bsky.socialTwo more DIG papers accepted at #EMNLP2026 (Budapest, Oct 24–29): one in the main conference, one in Findings. Both find events in multivariate time series from a natural-language description, with little or no labeled data. 🧵👇
@saravera.bsky.socialI'll be present at REALM 2026 Workshop at EMNLP to present this work. See you in Budapest! :)
đź“„: arxiv.org/abs/2609.17306
#REALM #EMNLP2026
@martinlukk.bsky.socialIs AI biased against some demographic groups? 🤔
Recent LLM audits disagree, finding both âž• and âž– discrimination, even for the same models.
In a new paper, accepted at #EMNLP2026 Findings, I show that this disagreement can arise from differences in audit format!
🧵 (1/7)
@haiyuesong.bsky.social🎉 Excited to share that our paper "OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training" has been accepted to EMNLP 2026 Main! See you in Budapest!
đź“„ Paper: arxiv.org/abs/2603.28858
#EMNLP2026 #ModelMerging #ContinualPretraining #BayesianOptimization
@terrytangyuan.xyz🎉 Excited to share that our paper "VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities” has been accepted to EMNLP 2026!
đź“„ Paper: arxiv.org/abs/2609.08040
#EMNLP2026 #AI #LLM #LLMAgents #Cybersecurity #SoftwareSupplyChain #OpenSource #RedHat
@kleines-gespenst.bsky.socialLooking forward to meeting the #NLProc community at #EMNLP2026 in Budapest and discussing the work there!
@kleines-gespenst.bsky.socialDo LMs have word order preferences & are they architectural or data-driven?
In our paper, the same architecture robustly prefers left-branching artificial languages, but on natural languages, as training data grows, right-branching SVOs win 🧵
Accepted to #EMNLP2026 main 🎉
@katrohrbacher.bsky.socialNew paper accepted to #EMNLP2026 main conference! We compare worldbuilding strategies in 8,000 stories across four LLMs with a human-authored baseline from Project Gutenberg, in English and German, focusing on setting and narrative space.
arxiv.org/abs/2609.02482
@rashonpoole.bsky.socialExcited to share that our paper “Personalizing LLMs Through User Value Profiles” has been accepted to @emnlpmeeting.bsky.social 2026 Main Track! #emnlp2026
@pathulith.bsky.social1/ 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.
🧵👇
@bayazitdeniz.bsky.social1/🚨 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. 🧵👇
