Excited to share our work on QASem Parsing, a text-to-text modeling of QA-based semantics! 🤩 Preprint: arxiv.org/abs/2205.11413 Code: github.com/kleinay/QASem Eran Hirsch @EliavRon Valentina Pyatkin Avi Caciularu IdoDagan

We are excited to share these papers by BIU NLP and collaborators accepted to #EMNLP2022! Come visit us next week EMNLP 2025 for more information, or see the thread below. cc (((ل()(ل() 'yoav))))👾 Reut Tsarfaty IdoDagan

🧠 New #ICLR2025 paper: "Explain Yourself, Briefly!" We introduce Sufficient Subset Training (SST)—a self-supervised method enabling neural networks to generate concise, faithful explanations as part of their predictions. 📄 Read more: arxiv.org/abs/2502.03391

🚨 Introducing LAQuer, accepted to #ACL2025 (main conf)! LAQuer provides more granular attribution for LLM generations: users can just highlight any output fact (top), and get attribution for that input snippet (bottom). This reduces the amount of text the user has to read by 2

🚨 CLATTER treats entailment as a reasoning process, guiding models to follow concrete steps (decomposition, attribution/entailment, and aggregation). CLATTER improves hallucination detection via NLI, with gains on ClaimVerify, LFQA, and TofuEval especially on long-reasoning

🚨 New preprint! We propose a reasoning process for hallucination detection: 1️⃣ Decompose the output 2️⃣ Generate fine-grained attribution (if possible), and accordingly make local entailment decisions 3️⃣ Aggregate all to a final decision We also introduce metrics to evaluate

🧵 New paper at Findings #ACL2025 ACL 2025! Not all documents are processed equally well. Some consistently yield poor results across many models. But why? And can we predict that in advance? Work with Steven Koniaev and Jackie Cheung Mila - Institut québécois d'IA McGill NLP #NLProc (1/n)

🚨 RAG is a popular approach but what happens when the retrieved sources provide conflicting information?🤔 We're excited to introduce our paper: “DRAGged into CONFLICTS: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs”🚀 A thread 🧵👇

🚨 New #ICML2025 paper! 𝐄𝐱𝐩𝐥𝐚𝐢𝐧𝐢𝐧𝐠, 𝐅𝐚𝐬𝐭 𝐚𝐧𝐝 𝐒𝐥𝐨𝐰 We generate explanations for neural networks 𝑒𝑓𝑓𝑖𝑐𝑖𝑒𝑛𝑡𝑙𝑦 and 𝑤𝑖𝑡ℎ 𝑝𝑟𝑜𝑣𝑎𝑏𝑙𝑒 𝑔𝑢𝑎𝑟𝑎𝑛𝑡𝑒𝑒𝑠 by pruning to a much smaller model and gradually expand it to ensure provable guarantees.

🎉 I am excited to present our new paper! Our paper improves personalization of text-to-image models, by adding one special cleaning step on top of existing personalized models. With just a single gradient update (~4 seconds on an NVIDIA H100 GPU) and a single image of the

Happy to share that our Image Captioning evaluation survey was accepted to TACL! I will be presenting the paper EMNLP 2025