Jing Liu
441
posts
@JLiu_Compuling
Paris, France
Joined June 2021
Always been impressed by Michael's work. Big congrats and look forward to more work!!!
Very excited to have been awarded a Google PhD fellowship in NLP for my work on mechanistic interpretability! Big thanks to
@Googleorgfor the support, as well as to my supervisors
@sandropezzelle@boknilevand
@ELLISforEuropefor all the help along the way.
I’m recruiting PhD students for 2026! If you are interested in robustness, training dynamics, interpretability for scientific understanding, or the science of LLM analysis you should apply. BU is building a huge LLM analysis/interp group and you’ll be joining at the ground floor.
this is quite surprising given the positive-only feedback performs better
Your casual LLM chats contain valuable learning signals - this paper shows how to use them Hidden feedback lurking in your LLM conversations can teach models to get better. Original Problem 🔍: LLMs struggle to learn from implicit feedback in multi-turn interactions without
i wonder whether this would also apply to text style transfer(TST)
Weaker is Better - Great paper from
@GoogleDeepMind**Problem**🔍: Training language models (LMs) on high-quality synthetic data from strong LMs is common for improving reasoning, but may not be compute-optimal under fixed inference budgets. **Key Insights from this Paper
This Post is from an account that no longer exists. Learn more
