Hayley Ross

@HayleyRossLing

PhD Student at @Harvard, working on computational semantics and LLM interpretability

Joined October 2010

Following

Followers

Replies Reposts Media

Hayley Ross
@HayleyRossLing
Apr 30, 2025
The tool-calling decision-making dataset I developed during my internship at NVIDIA is now out! Catch me presenting it at NAACL with @ameyasm1154 or see the 🧵 for details
Yoshi Suhara
@suhara
Apr 30, 2025
Check out a new dataset When2Call for training and evaluating LLMs on decision making about "when (not) to call" functions! 📄 Paper: aclanthology.org/2025.naacl-lon… 🤗 HF Dataset Hub: huggingface.co/datasets/nvidi… 💾 GitHub: github.com/nvidia/WHen2Ca… #NAACL2025
Hayley Ross
@HayleyRossLing
Apr 7, 2025
New paper with @najoungkim and @TeaAnd_OrCoffee! We previously found that humans and LLMs generalize to novel adjective-noun inferences (e.g. "Is a homemade currency still a currency?") Turns out analogy isn't enough to generalize, so it's likely evidence of composition! 🧵
Hayley Ross
@HayleyRossLing
Oct 24, 2024
New paper with @najoungkim and @TeaAnd_OrCoffee testing if LLMs can draw adjective-noun inferences like humans! Turns out they often can, and even generalize to unseen combinations. But they're more optimistic about "artificial intelligence" than humans. arxiv.org/abs/2410.17482
Hayley Ross
@HayleyRossLing
Apr 12, 2024
New preprint with @najoungkim & @TeaAnd_OrCoffee on fake reefs and other cases of (novel) adjective-noun composition: lingbuzz.net/lingbuzz/008012 Whether a fake N is an N or not depends on noun + context, but people handle novel AN pairs just fine 🙂 Stay tuned for results on LLMs!
Hayley Ross
@HayleyRossLing
Aug 21, 2013
@ootboxford When will we be able to download Blueprints from the ootb homepage? I can't wait to listen to it!