Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Feng, Jiahai"'
Language models are susceptible to bias, sycophancy, backdoors, and other tendencies that lead to unfaithful responses to the input context. Interpreting internal states of language models could help monitor and correct unfaithful behavior. We hypoth
Externí odkaz:
http://arxiv.org/abs/2406.19501
Autor:
Wong, Lionel, Mao, Jiayuan, Sharma, Pratyusha, Siegel, Zachary S., Feng, Jiahai, Korneev, Noa, Tenenbaum, Joshua B., Andreas, Jacob
Effective planning in the real world requires not only world knowledge, but the ability to leverage that knowledge to build the right representation of the task at hand. Decades of hierarchical planning techniques have used domain-specific temporal a
Externí odkaz:
http://arxiv.org/abs/2312.08566
Autor:
Feng, Jiahai, Steinhardt, Jacob
To correctly use in-context information, language models (LMs) must bind entities to their attributes. For example, given a context describing a "green square" and a "blue circle", LMs must bind the shapes to their respective colors. We analyze LM re
Externí odkaz:
http://arxiv.org/abs/2310.17191
Human language offers a powerful window into our thoughts -- we tell stories, give explanations, and express our beliefs and goals through words. Abundant evidence also suggests that language plays a developmental role in structuring our learning. He
Externí odkaz:
http://arxiv.org/abs/2205.05718
Publikováno v:
34th Conference on Neural Information Processing Systems (Neurips 2020), Vancouver, Canada
We present an improved method for symbolic regression that seeks to fit data to formulas that are Pareto-optimal, in the sense of having the best accuracy for a given complexity. It improves on the previous state-of-the-art by typically being orders
Externí odkaz:
http://arxiv.org/abs/2006.10782