RT @lkopf_ml: 🔍 When do neurons encode multiple concepts?. We introduce PRISM, a framework for extracting multi-concept feature description….

We conduct an evaluation of several LLMs on CoXQL using different parsing strategies. Our parsing approach with template validations (MP+) surpasses the performance of previous approaches. We also discover that intents with multiple slots remain highly challenging for LLMs.

We contribute to conversational explainable artificial intelligence (ConvXAI) systems based on large language models (LLMs) by filling the gap of training data and covering a broad range of XAI methods to map user requests onto.

Accepted at #EMNLP2024: CoXQL, an NLP dataset for user intent recognition in Conversational XAI. @qiaw991 will present his work in Miami later today at 4:00PM local time @ Poster Session C (Riverfront Hall). ACL Anthology: GitHub:

RT @naaclmeeting: 📢 NAACL needs Reviewers & Area Chairs! 📝. If you haven't received an invite for ARR Oct 2024 & want to contribute, sign….

Presenting my poster at @inlgmeeting today on political bias evaluation assessing sycophancy in (German-language) LLMs:. ACL Anthology: . This paper resulted from the great Bachelor thesis of Maximilian Bleick co-supervised with @albu and Sebastian Möller.

RT @BlackboxNLP: The submission deadline (15 aug) for BlackboxNLP is slowly approaching! We're very excited to see your approaches to open….

RT @ReviewAcl: If you haven't been invited to review for ARR 2024 June but are interested in helping us, please fill out this form by June….

RT @MCourtois173: Excited to share our paper, "Symmetric Dot-Product Attention for Efficient Training of BERT Language Models," accepted at….

RT @InseqLib: @InseqLib v0.6 is out now on PyPI! 🔥. New CLI command for context attribution (@gsarti_), new perturbation-based methods by @….

RT @bifoldberlin: New open #phd position: Contribute to the "FakeXplain - Development of transparent and meaningful explanations in the dis….

Thanks a lot to all emergency reviewers who helped fill in the gaps for the #ARR February 2024 cycle! 🫶 .We're good to go for the author response period.

RT @lasha_nlp: Looking for potential emergency reviewers for submissions in Interpretability and Model Analysis/NLP Applications! Topics in….

DMs are open. Replies are also welcome. First-time duty as AE for me and I'm honored to be in this position. Overall, the quality of reviews so far is high and only very few are missing as of now.

Looking for emergency reviewers for #ARR #ACL2024 #ACL2024nlp in the Interpretability and Analysis of Models for NLP track. Topics: Feature attribution, explanation evaluation for classification tasks, instance attribution. Deadline for reviews: March 24.

RT @InseqLib: Value Zeroing, a faithful approach for analyzing context mixing in Transformers, is now available on @InseqLib main branch fo….

You can find it in the ACL Anthology as well now:

Our InterroLang #EMNLP2023 Findings paper is presented a second time in today's first session -- starting now! Join us at booth 11A in the East lobby!

RT @InseqLib: @InseqLib v0.5 is finally out! 🐛 New tutorial, distributed and 4-bit quantized models, easier & better contrastive attributio….

Presenting "InterroLang" at the @BlackboxNLP Workshop of #EMNLP2023 now until 12:30 PM.