Rem Hida

Engineer / Ph.D. student / Views are my own.

[Rem Hida @rem_h4_]

Beyond fixed-turn, pre-scripted evaluations, we find that social bias in multi-turn LLM interactions can emerge late, fluctuate across turns, and re-emerge. These results highlight the need to evaluate social bias as a dynamic phenomenon.

Paper: https://t.co/GISKtZiH9L
［2/2］

[Rem Hida @rem_h4_]

Two long papers accepted to #EMNLP2026: a first-authored paper on fairness (Findings) and a co-authored paper on machine translation (Main Conference).

More info soon!

[Rem Hida @rem_h4_]

1st paper w/@MasahiroKaneko_ @dai0NLP @Bollegala @chokkanorg

We study social bias in response-conditioned multi-turn LLM interactions, where follow-up user queries adapt to the evolving dialogue which can vary in length.

［1/2］

[Prof. Danushka Bollegala @Bollegala]

We have two papers accepted to EMNLP 2026🎊
- Cross-Lingual Representation Alignment by Token-Level Optimal Transport in a Language-Agnostic Space (main)
Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala, Hitomi Yanaka @verypluming

- DyMT-ESB: Dynamic Multi-Turn Evaluation of Social Bias in User-LLM Interactions (Findings)
Rem Hida, Masahiro Kaneko, Daisuke Oba, Danushka Bollegala, Naoaki Okazaki @rem_h4_ @MasahiroKaneko_ @dai0NLP

Congrats to all my collaborators! #LiverpoolNLP

[Daisuke OBA @dai0NLP]

Our paper has been accepted to Findings of #EMNLP2026. This work brings bias evaluation of LLMs into more realistic settings.
Led by @rem_h4_ , with @MasahiroKaneko_, @Bollegala , and @chokkanorg. Details coming soon.

[ritvik @ritvikc1512]

主著1件が EMNLP 2026の Main 採択！！
人生初のヨーロッパで楽しみすぎる

Our work on efficient context use in machine translation has been accepted to the main conference of EMNLP 2026!

Looking forward to Budapest 🎉

[Rem Hida @rem_h4_]

@yangliu_nlp Thanks!🙇‍♀️

[Rem Hida @rem_h4_]

My citation count has surpassed 100! I’m deeply grateful to all my co-authors, and I’ll keep working hard to contribute even more.

[Masahiro Kaneko @MasahiroKaneko_]

Two first-author long papers accepted to #EMNLP2025 main, and one co-authored long paper in Findings 🎉 Thanks @rem_h4_, @AlhamFikri, @chokkanorg, and @eltimster! All on arXiv📜
- https://t.co/Uvu34nkxEi
- https://t.co/GTnDMz7Hof
- https://t.co/bGfw7GHWl5

[Rem Hida @rem_h4_]

One first-author long paper on fairness and one co-authored long paper on machine translation accepted to the Findings of #EMNLP2025.

More info soon. See you in Suzhou!

[Rem Hida @rem_h4_]

Our preprint (w/@MasahiroKaneko_ , @chokkanorg) demonstrates how prompt variations affect LLMs' performance and social biases. Our analysis reveals significant sensitivity to prompts and a tradeoff between performance and bias.
Paper: https://t.co/wpBmQiJiou