📢 ARR-May reviewers can now try REVAS, an experimental review support tool. REVAS gives feedback on review quality criteria and ARR reviewer heuristics, but does not suggest review content or scores. 🔗 aclrollingreview.org/revas-may26 #ARR #EMNLP #ACL #NLProc

"An article about computational science in a scientific publication is not the scholarship itself, it is merely advertising of the scholarship." Claerbout, 1992 Decades later, code is routinely released with papers. But does the code match the ad?

REVAS is a peer review assistant I've been working on with colleagues at MBZUAI. The idea is simple: better reviews make better science. If you're reviewing for ARR this cycle, give it a try.

💡 TIL @overleaf.com is basically a git repo. In my research workflow, I directly added it as submodule to my code repo. Now I can produce figures and tables, and have them magically uploaded to Overleaf just by pushing the repo. No more renaming, keeping versions straight, and manual uploading 😇

💡 TIL, it's super easy to fetch data from Google Sheets into Pandas. Makes it really convenient to annotate some data. Previously, I was always downloading CSVs, losing track of file versions, and loading and merging them sluggishly in Python. 👉 find the code here: gist.github.com/timbmg/6c2d6...

🔍 𝗪𝗮𝗻𝘁 𝘁𝗼 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗲 𝗺𝗼𝗱𝗲𝗹𝘀 𝗼𝗻 𝘀𝗰𝗶𝗲𝗻𝘁𝗶𝗳𝗶𝗰 𝗤𝗔, 𝗯𝘂𝘁 𝘆𝗼𝘂𝗿 𝗱𝗮𝘁𝗮𝘀𝗲𝘁 𝗹𝗮𝗰𝗸𝘀 𝗿𝗲𝗮𝗹-𝘄𝗼𝗿𝗹𝗱 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻𝘀 𝗮𝘀𝗸𝗲𝗱 𝗯𝘆 𝗲𝘅𝗽𝗲𝗿𝘁𝘀? 🚀 PeerQA is the solution: a dataset with questions from peer reviews and answers from the original authors. (1/🧵) #NLProc

🚨🚨 New preprint 🚨🚨 Ever wonder whether verbalized CoTs correspond to the internal reasoning process of the model? We propose a novel parametric faithfulness approach, which erases information contained in CoT steps from the model parameters to assess CoT faithfulness. arxiv.org/abs/2502.14829

𝗙𝗮𝗰𝘁-𝗖𝗵𝗲𝗰𝗸𝗶𝗻𝗴 𝗶𝗻 𝘁𝗵𝗲 𝗔𝗴𝗲 𝗼𝗳 𝗔𝗜 – 𝗔 𝗧𝗮𝗹𝗸 𝗯𝘆 𝗜𝗿𝘆𝗻𝗮 𝗚𝘂𝗿𝗲𝘃𝘆𝗰𝗵 @𝗔𝗜 𝗳𝗼𝗿 𝗚𝗼𝗼𝗱 Misinformation is a new weapon disrupting public debates, scientific discussions, and political decisions. How can we identify and counter misleading content? (1/🧵)

🤔 An Energy Star for AI? Introducing AI Energy Score: First-ever rating system comparing 166 AI models' energy consumption! From LLaMa to Gemma, get transparent ⭐️1-5 efficiency ratings. Incredible work led by @sashamtl.bsky.social huggingface.co/blog/sasha/a...

Excited to share that our Paper "PeerQA: A Scientific Question Answering Dataset from Peer Reviews" as been accepted to #NAACL2025 Looking forward to presenting it in Albuquerque 🏜️!

What do YOU mean by "intelligence", and does ChatGPT fit your definition? We collected the major criteria used in CogSci and other fields, and designed a survey to find out! Access link: www.survey-xact.dk/collect Code: 4S7V-SN4M-S536 Time: 5-10 mins