Gokhan Tur
@gokhantur.bsky.social
Professor, UIUC
Conversational AI
Conversational AI
Reposted by Gokhan Tur
ConvAI had a great NeurIPS season with four accepted papers to the main conference🎉 Find all the authors in San Diego this December ☀️
September 20, 2025 at 3:17 PM
ConvAI had a great NeurIPS season with four accepted papers to the main conference🎉 Find all the authors in San Diego this December ☀️
Reposted by Gokhan Tur
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/...
📄Arxiv: arxiv.org/pdf/2505.07775
💻 GitHub: github.com/beyzabozdag/...
May 13, 2025 at 8:12 PM
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/...
📄Arxiv: arxiv.org/pdf/2505.07775
💻 GitHub: github.com/beyzabozdag/...
Reposted by Gokhan Tur
We won a Senior Area Chair Award at NAACL!! Many thanks again to my amazing coauthors Gaurav Kamath and @sivareddyg.bsky.social :-)
May 3, 2025 at 3:51 PM
We won a Senior Area Chair Award at NAACL!! Many thanks again to my amazing coauthors Gaurav Kamath and @sivareddyg.bsky.social :-)
Reposted by Gokhan Tur
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
May 1, 2025 at 2:30 PM
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
Reposted by Gokhan Tur
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...
March 11, 2025 at 3:10 PM
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...
Reposted by Gokhan Tur
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:
It's also important to recognize the incredible works that helped us build SafeArena:
March 10, 2025 at 5:45 PM
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:
It's also important to recognize the incredible works that helped us build SafeArena:
Reposted by Gokhan Tur
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 👇
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 👇
March 10, 2025 at 5:45 PM
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 👇
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 👇
Reposted by Gokhan Tur
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.
[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/
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/
March 5, 2025 at 5:54 AM
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.
Reposted by Gokhan Tur
[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/
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/
March 4, 2025 at 5:28 PM
[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/
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/
Reposted by Gokhan Tur
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… 🧵
We examine constituent ordering preferences between humans and LLMs; we present two main findings… 🧵
February 19, 2025 at 7:31 PM
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… 🧵
We examine constituent ordering preferences between humans and LLMs; we present two main findings… 🧵
Reposted by Gokhan Tur
🚀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!
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!
February 17, 2025 at 4:06 AM
🚀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!
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!
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!
🚀Can a Single Model Master Both Multi-turn Conversations and Tool Use?
Introducing CALM, fully open-source Conversational Agentic Language Models with CALM 8B, CALM 70B, and CALM 405B-excelling in both multi-turn dialogue management & function calling.
🌐Project Page: emrecanacikgoz.github.io/CALM/
Introducing CALM, fully open-source Conversational Agentic Language Models with CALM 8B, CALM 70B, and CALM 405B-excelling in both multi-turn dialogue management & function calling.
🌐Project Page: emrecanacikgoz.github.io/CALM/
February 14, 2025 at 6:57 PM
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!
Reposted by Gokhan Tur
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!
💡 Introducing Reference-Level Feedback: A new paradigm for using feedback to improve synthetic data!
🌐 shuhaibm.github.io/refed/
🧵 [1/n]
🌐 shuhaibm.github.io/refed/
🧵 [1/n]
February 10, 2025 at 7:43 PM
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!
Reposted by Gokhan Tur
💡 Introducing Reference-Level Feedback: A new paradigm for using feedback to improve synthetic data!
🌐 shuhaibm.github.io/refed/
🧵 [1/n]
🌐 shuhaibm.github.io/refed/
🧵 [1/n]
February 10, 2025 at 3:56 PM
💡 Introducing Reference-Level Feedback: A new paradigm for using feedback to improve synthetic data!
🌐 shuhaibm.github.io/refed/
🧵 [1/n]
🌐 shuhaibm.github.io/refed/
🧵 [1/n]
Reposted by Gokhan Tur
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
@convai-uiuc.bsky.social @gokhantur.bsky.social
‼️ 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...
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...
February 9, 2025 at 12:54 AM
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
@convai-uiuc.bsky.social @gokhantur.bsky.social
Reposted by Gokhan Tur
‼️ 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...
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...
February 8, 2025 at 10:42 PM
‼️ 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...
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...
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 👏
Congratulations to @dilekh.bsky.social for her ACL Fellowship! 🎉🎉🎉 www.aclweb.org/portal/conte...
ACL Fellows 2024 | ACL Member Portal
www.aclweb.org
December 11, 2024 at 2:53 PM
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 👏
Nice overview of the ReSpAct framework for conversational task completion agents @convai-uiuc.bsky.social
cobusgreyling.medium.com/building-con...
cobusgreyling.medium.com/building-con...
Building Conversational AI Agents By Integrating Reasoning, Speaking & Acting With LLMs
AI Agents meet Conversational UI for intuitive & natural conversations.
cobusgreyling.medium.com
November 19, 2024 at 8:29 PM
Nice overview of the ReSpAct framework for conversational task completion agents @convai-uiuc.bsky.social
cobusgreyling.medium.com/building-con...
cobusgreyling.medium.com/building-con...
@chrupala.me please add me in to the SLP pack
November 19, 2024 at 3:49 PM
@chrupala.me please add me in to the SLP pack