Zobrazeno 1 - 10
of 57 601
pro vyhledávání: '"Ackerman, IN"'
It has been reported that LLMs can recognize their own writing. As this has potential implications for AI safety, yet is relatively understudied, we investigate the phenomenon, seeking to establish whether it robustly occurs at the behavioral level,
Externí odkaz:
http://arxiv.org/abs/2410.02064
Autor:
Ackerman, Christopher M.
Activation engineering is becoming increasingly popular as a means of online control of large language models (LLMs). In this work, I extend the idea of active steering with vectors that represent a behavioral direction of interest to tuning those ve
Externí odkaz:
http://arxiv.org/abs/2409.06927
Neuroimaging studies, such as the Human Connectome Project (HCP), often collect multi-faceted and multi-block data to study the complex human brain. However, these data are often analyzed in a pairwise fashion, which can hinder our understanding of h
Externí odkaz:
http://arxiv.org/abs/2408.16791
Autor:
Diepeveen, N. A., Pereira, C. Robalo, Mazzanti, M., Ackerman, Z. E. D., Gallagher, L. P. H., Timmerman, T., Gerritsma, R., Schüssler, R. X.
We present spectroscopic data for four metastable state clear-out transitions between 399 nm and 412 nm for all even long-lived isotopes of Yb$^+$ as well as their hyperfine structure in $^{171}$Yb$^+$. The strong $^2 \rm{D}_{3/2} \rightarrow {}^1[1/
Externí odkaz:
http://arxiv.org/abs/2408.07380
Autor:
Patton, William, Rhoades, Jeff L., Zouinkhi, Marwan, Ackerman, David G., Malin-Mayor, Caroline, Adjavon, Diane, Heinrich, Larissa, Bennett, Davis, Zubov, Yurii, Team, CellMap Project, Weigel, Aubrey V., Funke, Jan
DaCapo is a specialized deep learning library tailored to expedite the training and application of existing machine learning approaches on large, near-isotropic image data. In this correspondence, we introduce DaCapo's unique features optimized for t
Externí odkaz:
http://arxiv.org/abs/2408.02834
We evaluate the robustness of several large language models on multiple datasets. Robustness here refers to the relative insensitivity of the model's answers to meaning-preserving variants of their input. Benchmark datasets are constructed by introdu
Externí odkaz:
http://arxiv.org/abs/2408.01963
Autor:
Doerfler, Periwinkle, Turk, Kieron Ivy, Geeng, Chris, McCoy, Damon, Ackerman, Jeffrey, Dragiewicz, Molly
In this work, we analyze two large-scale surveys to examine how individuals think about sharing smartphone access with romantic partners as a function of trust in relationships. We find that the majority of couples have access to each others' devices
Externí odkaz:
http://arxiv.org/abs/2407.04906
Autor:
Mazzanti, M., Pereira, C. Robalo, Diepeveen, N. A., Gerritsen, B., Wu, Z., Ackerman, Z. E. D., Gallagher, L. P. H., Safavi-Naini, A., Gerritsma, R., Schüssler, R. X.
This paper presents a routine to align an optical tweezer on a single trapped ion and use the ion as a probe to characterize the tweezer. We find a smallest tweezer waist of $2.3(2)\,\mu$m, which is in agreement with the theoretical minimal attainabl
Externí odkaz:
http://arxiv.org/abs/2406.06721
A long-standing open conjecture of Branko Gr\"unbaum from 1972 states that any simple arrangement of $n$ pairwise intersecting pseudocircles in the plane can have at most $2n-2$ digons. Agarwal et al. proved this conjecture for arrangements of pairwi
Externí odkaz:
http://arxiv.org/abs/2406.02276
We introduce a novel LLM based solution design approach that utilizes combinatorial optimization and sampling. Specifically, a set of factors that influence the quality of the solution are identified. They typically include factors that represent pro
Externí odkaz:
http://arxiv.org/abs/2405.13020