Glad to hear ❤️

📄 Paper: arxiv.org/abs/2505.19299
💻 Code: github.com/lingjunzhao/PE…
🙏 Huge thanks to my advisor @haldaume3.bsky.social and everyone who shared insights!

🚨 New #EMNLP2025 (main) paper!
LLMs often produce inconsistent explanations (62–86%), hurting faithfulness and trust in explainable AI.
We introduce PEX consistency, a measure for explanation consistency,
and show that optimizing it via DPO improves faithfulness by up to 9.7%.

What should Machine Translation research look like in the age of multilingual LLMs?

Here’s one answer from researchers across NLP/MT, Translation Studies, and HCI.
"An Interdisciplinary Approach to Human-Centered Machine Translation"
arxiv.org/abs/2506.13468

Do you like trivia? Can you spot when AI is feeding you BS? Or can you make AIs turn themselves inside out? Then on June 14 at College Park (or June 21 online), we have a competition for you.

Super thankful for my wonderful collaborators: @pcascanteb.bsky.social @haldaume3.bsky.social Mingyang Xie, Kwonjoon Lee

We introduce a super simple yet effective strategy to improve video-language alignment (+18%): add hallucination correction in your training objective👌
Excited to share our accepted paper at ACL: Can Hallucination Correction Improve Video-language Alignment?
Link: arxiv.org/abs/2502.15079

For the ACL ARR review, I’ve heard complaints about the workload—some reviewers have 16 papers. Even though I only need to write 1 rebuttal and respond to 4, it still feels substantial. For those managing more (thank you!), it can be difficult to thoroughly engage with every rebuttal.

There is a new version of the Research Plan for NIST's AI Safety Consortium (AISIC) in response to EOs. I did a diff.

Out: safety, responsibility, sociotechnical, fairness, working w fed agencies, authenticating content, watermarking, RN of CBRN, autonomous replication, ctrl of physical systems
>

This is my first time serving as an AC for a big conference.

Just read this great work by Goyal et al. arxiv.org/abs/2411.11437

I'm optimizing for high coverage and low redundancy—assigning reviewers based on relevant topics or affinity scores alone feels off. Seniority and diversity matter!