Anja Reusch
@anja.re
👩💻 Postdoc @ Technion, interested in Interpretability in IR 🔎 and NLP 💬
Reposted by Anja Reusch
(ICLR) How do LLMs perform arithmetic operations? Do they implement robust algorithms, or rely on heuristics? We find that they rely on a "bag of heuristics" that work well—but on a limited range of inputs.
Led by Yaniv Nikankin: arxiv.org/abs/2410.21272
Led by Yaniv Nikankin: arxiv.org/abs/2410.21272
Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
Do large language models (LLMs) solve reasoning tasks by learning robust generalizable algorithms, or do they memorize training data? To investigate this question, we use arithmetic reasoning as a rep...
arxiv.org
March 11, 2025 at 2:30 PM
(ICLR) How do LLMs perform arithmetic operations? Do they implement robust algorithms, or rely on heuristics? We find that they rely on a "bag of heuristics" that work well—but on a limited range of inputs.
Led by Yaniv Nikankin: arxiv.org/abs/2410.21272
Led by Yaniv Nikankin: arxiv.org/abs/2410.21272