iiinova — where your digital self keeps evolving

Reposted by Gokhan Tur

ConvAI @ UIUC @convai-uiuc.bsky.social · 20/09/2025

ConvAI had a great NeurIPS season with four accepted papers to the main conference🎉 Find all the authors in San Diego this December ☀️

141

Reposted by Gokhan Tur

Beyza Bozdag @beyzabozdag.bsky.social · 13/05/2025

Thrilled to announce our new survey that explores the exciting possibilities and troubling risks of computational persuasion in the era of LLMs 🤖💬 📄Arxiv: arxiv.org/pdf/2505.07775 💻 GitHub: github.com/beyzabozdag/...

195

Reposted by Gokhan Tur

Ada @adadtur.bsky.social · 03/05/2025

We won a Senior Area Chair Award at NAACL!! Many thanks again to my amazing coauthors Gaurav Kamath and @sivareddyg.bsky.social :-)

2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Linguistic Theories, Cognitive Modeling, and Psycholinguistics Senior Area Chair Award presented to Ada Tur, Gaurav Kamath, and Siva Reddy. May 2, 2025. Signed by Colin Cherry (General Chair), Luis Chiruzzo, Alan Ritter, and Lu Wang (Program Chairs)

0132

Reposted by Gokhan Tur

Mila - Institut québécois d'IA @mila-quebec.bsky.social · 01/05/2025

Congratulations to Mila members @adadtur.bsky.social , Gaurav Kamath and @sivareddyg.bsky.social for their SAC award at NAACL! Check out Ada's talk in Session I: Oral/Poster 6. Paper: arxiv.org/abs/2502.05670

0137

Reposted by Gokhan Tur

Ada @adadtur.bsky.social · 11/03/2025

Super excited that this is finally out! We evaluated leading LLM-based web agents from OpenAI, Anthropic, and more, on our new benchmark SafeArena and found that many are surprisingly compliant with malicious requests. Check out the leaderboard here: huggingface.co/spaces/McGil...

huggingface.co

Safearena Leaderboard - a Hugging Face Space by McGill-NLP

SafeArena Leaderboard

081

Reposted by Gokhan Tur

Xing Han Lu @xhluca.bsky.social · 10/03/2025

This work was done by an awesome team of authors: @adadtur.bsky.social, Nick, @arkil.bsky.social, @karstanczak.bsky.social, Esin, @spandanagella.bsky.social, and @sivareddyg.bsky.social. It's also important to recognize the incredible works that helped us build SafeArena:

141

Reposted by Gokhan Tur

Xing Han Lu @xhluca.bsky.social · 10/03/2025

Agents like OpenAI Operator can solve complex computer tasks, but what happens when users use them to cause harm, e.g. spread misinformation? To find out, we introduce SafeArena (safearena.github.io), a benchmark to assess the capabilities of web agents to complete harmful web tasks. A thread 👇

1167

Reposted by Gokhan Tur

Dilek Hakkani-Tur @dilekh.bsky.social · 05/03/2025

While persuasive models are promising for social good, they can also be misused towards harmful behavior. Recent work by @beyzabozdag.bsky.social and @shuhaib.bsky.social aims to assess LLM persuasiveness and susceptibility towards persuasion.

052

Reposted by Gokhan Tur

Beyza Bozdag @beyzabozdag.bsky.social · 04/03/2025

[1/6] Can LLMs out-persuade each other? 🤖🧠💬 Introducing Persuade Me If You Can (PMIYC)—a new framework to evaluate (1) how persuasive LLMs are and (2) how easily they can be persuaded! 🚀 📄Arxiv: arxiv.org/abs/2503.01829 🌐Project Page: beyzabozdag.github.io/PMIYC/

192

Reposted by Gokhan Tur

Ada @adadtur.bsky.social · 19/02/2025

Super excited to finally announce our NAACL 2025 main conference paper “Language Models Largely Exhibit Human-like Constituent Ordering Preferences”! We examine constituent ordering preferences between humans and LLMs; we present two main findings… 🧵

Overview figure for paper, showing creation of constituent movement data, in addition to three step experimentation: "Model Shifting Preference", "Motivating Factors of Model Preference", "Human-Model Preference Correlation"

152

Reposted by Gokhan Tur

Ishika Agarwal @wonderingishika.bsky.social · 17/02/2025

🚀Very excited about my new paper! NN-CIFT slashes data valuation costs by 99% using tiny neural nets (205k params, just 0.0027% of 8B LLMs) while maintaining top-tier performance!

1114

Gokhan Tur @gokhantur.bsky.social · 14/02/2025

The secret sauce for this work is the ReAct style training data preparation: “User-Thought1-Action/API-Observation-Thought2-Response”. We transformed public dialogue datasets into this format for training. Congratulations to @emrecanacikgoz and the @convai_uiuc and Oumi teams!

021

Reposted by Gokhan Tur

Dilek Hakkani-Tur @dilekh.bsky.social · 10/02/2025

Instruction data can also be synthesized using feedback based on reference examples. Please check our recent work for more information. Thanks to @shuhaib.bsky.social, Xiusi Chen, and Heng Ji!

041

Reposted by Gokhan Tur

Shuhaib Mehri @shuhaib.bsky.social · 10/02/2025

💡 Introducing Reference-Level Feedback: A new paradigm for using feedback to improve synthetic data! 🌐 shuhaibm.github.io/refed/ 🧵 [1/n]

162

Reposted by Gokhan Tur

Dilek Hakkani-Tur @dilekh.bsky.social · 09/02/2025

AI over-reliance is an important issue for conversational agents. Our work supported mainly by the DARPA FACT program proposes introducing positive friction to encourage users to think critically when making decisions. Great team-work, all! @convai-uiuc.bsky.social @gokhantur.bsky.social

0103

Reposted by Gokhan Tur

Mert İnan @merterm.bsky.social · 08/02/2025

‼️ Ever wish LLMs would just... slow down for a second? In our latest work, "Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems", we delve into how strategic delays can enhance dialogue systems. Paper Website: merterm.github.io/positive-fri...

1155

Gokhan Tur @gokhantur.bsky.social · 11/12/2024

Seeing this year's ACL Fellows is like walking through the hallways of Microsoft Research, Building 99 in 2016. Congratulations @dilekh.bsky.social Scott Yih, Jianfeng Gao, and Lucy Vanderwende 👏

0100