Min Zhang

@IR_oldie Thanks for the interests. When one LLM is used as the evaluator, it works differently from as an answerer. Just like asking one student to evaluate another one’s homework. Btw: We also use other LLMs, such as Claude, to evaluate GPT etc, and the results do not change much.

"A User-Centric Multi-Intent Benchmark for Evaluating Large Language Models" Using GPT-4 to evaluate other LLMs and to evaluate GPT-4 output. Results make the case that this sort of recursive evaluation is OK. Hmmm, do I agree? Not sure #enlp2024 aclanthology.org/2024.emnlp-mai…

#NeurIPS Shame on the offensive slides, which is obvious by design. Shame on the speaker’s response during the QA. We DO teach moral and values at school. Taking the personal racism into the academic conference is really harmful to the whole community.

@NeurIPSConf Shame on the offensive slides, which is obvious by design. Shame on the speaker’s response during the QA. We DO teach moral and values at school. Taking the personal racism into the academic conference is really harmful to the whole community.

NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by making generalisations about Chinese scholars. This is not what NeurIPS stands for. NeurIPS is dedicated to being a safe space for all of us. We want to address the comment made during the invited talk this afternoon, as it is something that NeurIPS does not condone and it doesn't align with our code of conduct. We are addressing this issue with the speaker directly. NeurIPS is dedicated to being a diverse and inclusive place where everyone is treated equally.

@xwang_lk Shame on the offensive slides, which is obvious by design. Shame on the speaker’s response during the QA. We DO teach moral and values at school. Taking the personal racism into the academic conference is really harmful to the whole community.

It is just so sad that the #NeurIPS2024 main conference ended with such a racist remark by a faculty when talking about ethics. How ironic! I also want to commend the Chinese student who spoke up right on spot. She was respectful, decent, and courageous. Her response was exemplary: she began by acknowledging the speaker’s efforts, then gave the speaker an opportunity to clarify (though, regrettably, the speaker’s reply only reinforced her bias), and ultimately called attention to the inappropriate racial bias and offered constructive suggestions. Thank you for speaking out!

@tetsuyasakai So sorry for your loss. R.I.P. 愿逝者安息，也请您节哀

母、大往生を遂げました Thank you Mother

Please help join us with A Survey on User Fitness and Exercise Pref.: forms.gle/iNxJXykeyx2CwH… 🕰 The survey takes approximately 5 min. 🟢 Your responses are anonymous and will only be used for overall analysis. It is a pre-study of the fitness recom research. Thank you!

The deadline of the TOIS Special Section on "Causality Representation Learning in LLM-Driven Recommender Systems" has been extended to Sep. 30, 2024. Are you ready to submit?

Congratulations to our students and faculties from @thuir_lab , #DCST , Tsinghua Uni. for winning #sigir24 Best Paper Award! Proud of you!

We @thuir_lab are honored to receive the Test-of-Time Award from #SIGIR2024! Thank you @yongfengzhang9，Guokun, colleagues Yiqun, Prof Ma, and collaborators Prof. Yi Zhang! Let’s keep going on Explainable Recommendation!

We're working on a Survey on User Experience with Large Language Models 🕰️ 14 questions, takes around 5-10 minutes. 🟢 It does not record your personal information; all responses are only used for overall analysis. ➡️ Welcome to participate: wjx.cn/vm/eUgtfJq.asp… #survey

It is truly inspiring to engage in discussions with professors from Philosophy, Psychology, History, Art, and Literature. Attending the “Technology and Life: Reflection across Disciplines” conference at the University of Macau.

Call For ACM TOIS Special Section on Pre-trained Models for Search and Recommendation. The submission entry has already opened. Deadline: Feb 1, 2024.

A huge thanks to our distinguished reviewers! #CIKM2023

Late message: It's my great pleasure to work with @mounialalmas and @rodrygo_santos as the PC co-chairs, together with GCs @iFromm, @FTHopf, Mark Lee, and Michael Oakes. We tried our best and made great efforts to make it and enjoyed a wonderful time at #CIKM2023. See you in 2024

Glad to share the news that TOIS received from ACM: "I am delighted to inform you that, due to the journal's strong performance, the decision has been made to increase the frequency for TOIS from 4 to 6 issues per year beginning with the 2024 volume."

#CIKM2023 Our THUIR student Bulou Liu will present our paper “Leveraging Event Schema to Ask Clarifying Questions for Conversational Legal Case Retrieval”, Wed. 25 Oct., Session 8C - Dialogue Systems - Belmont 2 , at 2:45pm Paper in the DL: dl.acm.org/doi/10.1145/35…

#CIKM2023 Our student @Qian Dong will be presenting our paper “I3Retriever: Incorporating Implicit Interaction in Pre-trained Language Models for Passage Retrieval”, Mon. 23 Oct, Session 1H- Ashtead 3, at 11:00am ​Paper at ACM DL: dl.acm.org/doi/10.1145/35…

#CIKM2023 My student @Nicole_He will present our paper "Understanding User Immersion in Online Short Video Interaction", Mon. 23 Oct., Session 3E - Meeting Room 2, at 17:45pm. Join us and dive into the world of user immersion! Paper in the ACM DL: dl.acm.org/doi/10.1145/35…

Heading to #CIKM2023 in Birmingham, UK! Very excited to connect with many of you. My PC co-chairs, @rodrygo_santos and @mzhang_bj, and I have put in a lot of effort into the programme. We hope you enjoy it!