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
Research Fellow @ RBC Borealis
Model analysis, interpretability, reasoning and hallucination
Studying model behaviours to make them better :))
Looking for Fall '26 PhD
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
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
July 28, 2025 at 9:18 AM
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
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
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
June 6, 2025 at 6:11 PM
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
These examples show answers — even to the same query — can shift under different irrelevant contexts. Can we predict these shifts? 2/n
June 6, 2025 at 6:10 PM
These examples show answers — even to the same query — can shift under different irrelevant contexts. Can we predict these shifts? 2/n
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
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
June 6, 2025 at 6:10 PM
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
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