RT @mirandrom: @cesare_spinoso @McGill_NLP @Mila_Quebec @aclmeeting

UPDATE: This will be in exhibition hall X5, poster board 55!.

RT @ziling_cheng: What do systematic hallucinations in LLMs tell us about their generalization abilities?. Come to our poster at #ACL2025 o….

How can we use models of cognition to help LLMs interpret figurative language (irony, hyperbole) in a more human-like manner? Come to our #ACL2025NLP poster on Wednesday at 11AM (exhibit hall - exact location TBA) to find out! @McGill_NLP @Mila_Quebec @aclmeeting

RT @ljyflores38: ⏰ Sharing our work on calibrated confidence scores at #ACL2025NLP, July 29 – 4PM Vienna time (Virtual)!. 📰 Improving the C….

Thanks to collaborators @DavidAustinCS , @PiantanidaPablo and Jackie Cheung. We also received some amazing feedback from the @Mila_Quebec @McGill_NLP community! And thanks to @_jennhu, Justine Kao and @tsvilodub for sharing their datasets.

Other cool findings:.1. We prove that (RSA)^2 is more expressive than QUD-based RSA. 2. Naively applying RSA to LLMs leads to probability 𝘴𝘱𝘳𝘦𝘢𝘥𝘪𝘯𝘨, not 𝘯𝘢𝘳𝘳𝘰𝘸𝘪𝘯𝘨! Are there better ways to use RSA & LLMs?.3. We design a rhetorical strategy clustering algorithm!.

What about LLMs? We integrate LLMs within (RSA)^2 and test them on a new dataset, PragMega+. We show that LLMs augmented with (RSA)^2 produce probability distributions which are more aligned with human expectations.

We test (RSA)^2 on two existing figurative language datasets: hyperbolic number expressions (e.g. “This kettle costs 1000$”) and ironic utterances about the weather (e.g. “The weather is amazing” during a Montreal blizzard). We obtain human-like meaning distributions!

Introducing (RSA)^2: a 𝘳𝘩𝘦𝘵𝘰𝘳𝘪𝘤𝘢𝘭-𝘴𝘵𝘳𝘢𝘵𝘦𝘨𝘺-𝘢𝘸𝘢𝘳𝘦 probabilistic framework of figurative language. In (RSA)^2 one listener will interpret language literally, another will interpret language ironically. Marginalization produces a distribution over meanings.

A blizzard is raging in Montreal when your friend says “Wow, the weather is amazing!” Humans easily interpret irony, while LLMs struggle at it. We propose a 𝘳𝘩𝘦𝘵𝘰𝘳𝘪𝘤𝘢𝘭-𝘴𝘵𝘳𝘢𝘵𝘦𝘨𝘺-𝘢𝘸𝘢𝘳𝘦 probabilistic framework as a solution. @ #acl2025

Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.

RT @Icannos: Thrilled to report that our work won Area Chair's Award!.You can find a nice high level explanation of our work!.Be sure to st….

RT @ian_porada: Do existing multi-dataset evaluations allow us to draw meaningful, reliable conclusions about coreference resolution models….

RT @bonadossou: 🚨 Thrilled to share that two of my papers have been accepted to @aclmeeting SRW 2025! 🧠🌍.They tackle key challenges in low-….

RT @oriern1: 🧵 New paper at Findings #ACL2025 @aclmeeting!.Not all documents are processed equally well. Some consistently yield poor resul….

RT @ljyflores38: ❗️ Confidence in text generation is tricky, as models can be confident in many, valid answers. 👀 Can we account for this….

RT @ziling_cheng: Do LLMs hallucinate randomly? Not quite. Our #ACL2025 (Main) paper shows that hallucinations under irrelevant contexts fo….

RT @ian_porada: LLMs that "solve" challenge sets might still be relatively inaccurate at resolving diverse, attested instances of the same….

Very happy to have presented my poster at the CustomNLP4U Workshop at EMNLP 2024 (@emnlpmeeting @customnlp4u).@McGill_NLP @Mila_Quebec #EMNLP

RT @jad_kabbara: Social Impact Award celebration with cool EMNLP folks! 🏆💫🎉. #EMNLP2024 @emnlpmeeting