iiinova — where your digital self keeps evolving

Ziling Cheng

@ziling-cheng.bsky.social

MSc Master's @mila-quebec.bsky.social @mcgill-nlp.bsky.social Research Fellow @ RBC Borealis Model analysis, interpretability, reasoning and hallucination Studying model behaviours to make them better :)) Looking for Fall '26 PhD

Posts Replies Media

Ziling Cheng @ziling-cheng.bsky.social · 28/07/2025

What do systematic hallucinations in LLMs tell us about their generalization abilities? Come to our poster at #ACL2025 on July 29th at 4 PM in Level 0, Halls X4/X5. Would love to chat about interpretability, hallucinations, and reasoning :) @mcgill-nlp.bsky.social @mila-quebec.bsky.social

022

Ziling Cheng @ziling-cheng.bsky.social · 06/06/2025

Turns out, we can. They follow a systematic failure mode we call class-based (mis)generalization: the model abstracts the class from the query (e.g., languages) and generalizes based on features from the irrelevant context (e.g., Honda → Japan). 3/n

160

Ziling Cheng @ziling-cheng.bsky.social · 06/06/2025

These examples show answers — even to the same query — can shift under different irrelevant contexts. Can we predict these shifts? 2/n

190

Ziling Cheng @ziling-cheng.bsky.social · 06/06/2025

Do LLMs hallucinate randomly? Not quite. Our #ACL2025 (Main) paper shows that hallucinations under irrelevant contexts follow a systematic failure mode — revealing how LLMs generalize using abstract classes + context cues, albeit unreliably. 📎 Paper: arxiv.org/abs/2505.22630 1/n

14517