iiinova — where your digital self keeps evolving

Jirui Qi @jiruiqi.bsky.social · 05/03/2026

Excited to kick off a 3-month research visit at Rycolab (ETH Zurich)! 🇨🇭 My research focuses on RL, alignment, multilingual LMs, reasoning, and RAG. If you're exploring any of these areas, feel free to reach out or say hi! #NLP #RL #AIAlignment #Multilinguality

060

Reposted by Jirui Qi

Arianna Bisazza @arianna-bis.bsky.social · 31/10/2025

InCLow topics #EMNLP2025: - MT error prediction techniques & its reception by professional translators (@gsarti.com) - thinking language in Large Reasoning Models (@jiruiqi.bsky.social) - effect of stereotypes on LLM’s implicit personalization (@veraneplenbroek.bsky.social) ....

151

Jirui Qi @jiruiqi.bsky.social · 20/08/2025

Our paper on multilingual reasoning is accepted to Findings of #EMNLP2025! 🎉 (OA: 3/3/3.5/4) We show SOTA LMs struggle with reasoning in non-English languages; prompt-hack & post-training improve alignment but trade off accuracy. 📄 arxiv.org/abs/2505.22888 See you in Suzhou! #EMNLP

arxiv.org

When Models Reason in Your Language: Controlling Thinking Trace Language Comes at the Cost of Accuracy

Recent Large Reasoning Models (LRMs) with thinking traces have shown strong performance on English reasoning tasks. However, their ability to think in other languages is less studied. This capability ...

073

Reposted by Jirui Qi

Gabriele Sarti @gsarti.com · 30/05/2025

📢 New paper: Can unsupervised metrics extracted from MT models detect their translation errors reliably? Do annotators even *agree* on what constitutes an error? 🧐 We compare uncertainty- and interp-based WQE metrics across 12 directions, with some surprising findings! 🧵 1/

1163

Jirui Qi @jiruiqi.bsky.social · 30/05/2025

[1/]💡New Paper Large reasoning models (LRMs) are strong in English — but how well do they reason in your language? Our latest work uncovers their limitation and a clear trade-off: Controlling Thinking Trace Language Comes at the Cost of Accuracy 📄Link: arxiv.org/abs/2505.22888

185

Jirui Qi @jiruiqi.bsky.social · 11/04/2025

✨ New Paper ✨ [1/] Retrieving passages from many languages can boost retrieval augmented generation (RAG) performance, but how good are LLMs at dealing with multilingual contexts in the prompt? 📄 Check it out: arxiv.org/abs/2504.00597 (w/ @arianna-bis.bsky.social @Raquel_Fernández) #NLProc

145

Jirui Qi @jiruiqi.bsky.social · 24/01/2025

🎉 First post on Blue: Our paper on **efficient prompt engineering** has been accepted by NAACL2025 Main Conference! 🎉 Key Point: LLMs tend to generate better responses when the likelihood of the question segment is higher. I.e. p(question) ∝ Performance Paper available at: arxiv.org/abs/2411.07773

arxiv.org

Likelihood as a Performance Gauge for Retrieval-Augmented Generation

Recent work finds that retrieval-augmented generation with large language models is prone to be influenced by the order of retrieved documents in the context. However, the lack of in-depth analysis li...

120