Zobrazeno 1 - 10
of 6 756
pro vyhledávání: '"A, Demartini"'
Recent advancements of generative LLMs (Large Language Models) have exhibited human-like language capabilities but have shown a lack of domain-specific understanding. Therefore, the research community has started the development of domain-specific LL
Externí odkaz:
http://arxiv.org/abs/2412.01189
Human-annotated content is often used to train machine learning (ML) models. However, recently, language and multi-modal foundational models have been used to replace and scale-up human annotator's efforts. This study compares human-generated and ML-
Externí odkaz:
http://arxiv.org/abs/2411.18968
Autor:
Ariai, Farid, Demartini, Gianluca
Natural Language Processing is revolutionizing the way legal professionals and laypersons operate in the legal field. The considerable potential for Natural Language Processing in the legal sector, especially in developing computational tools for var
Externí odkaz:
http://arxiv.org/abs/2410.21306
Aligning the output of Large Language Models (LLMs) with human preferences (e.g., by means of reinforcement learning with human feedback, or RLHF) is essential for ensuring their effectiveness in real-world scenarios. Despite significant advancements
Externí odkaz:
http://arxiv.org/abs/2410.16586
We present a novel approach for enhancing diversity and control in data annotation tasks by personalizing large language models (LLMs). We investigate the impact of injecting diverse persona descriptions into LLM prompts across two studies, exploring
Externí odkaz:
http://arxiv.org/abs/2410.11745
Autor:
DeMartini, D., Alhassid, Y.
We compute the magnetic dipole (M1) $\gamma$-ray strength functions ($\gamma$SF) for the odd-mass lanthanides $^{143-151}$Nd and $^{147-153}$Sm using the shell-model Monte Carlo method in combination with the static-path approximation and the maximum
Externí odkaz:
http://arxiv.org/abs/2410.00109
While model fairness improvement has been explored previously, existing methods invariably rely on adjusting explicit sensitive attribute values in order to improve model fairness in downstream tasks. However, we observe a trend in which sensitive de
Externí odkaz:
http://arxiv.org/abs/2409.18470
Autor:
Ballouz, R. -L., Agrusa, H., Barnouin, O. S., Walsh, K. J., Zhang, Y., Binzel, R. P., Bray, V. J., DellaGiustina, D. N., Jawin, E. R., DeMartini, J. V., Marusiak, A., Michel, P., Murdoch, N., Richardson, D. C., Rivera-Valentín, E. G., Rivkin, A. S., Tang, Y.
Spectral characterization of near-Earth asteroids (NEAs) has revealed a continuum of space-weathered states for the surfaces of S-complex NEAs, with Q-class NEAs, an S-complex subclass, most closely matching the un-weathered surfaces of ordinary chon
Externí odkaz:
http://arxiv.org/abs/2406.04864
To counter the side effect brought by the proliferation of social media platforms, hate speech detection (HSD) plays a vital role in halting the dissemination of toxic online posts at an early stage. However, given the ubiquitous topical communities
Externí odkaz:
http://arxiv.org/abs/2406.00046
Autor:
Agrusa, Harrison F., Zhang, Yun, Richardson, Derek C., Pravec, Petr, Ćuk, Matija, Michel, Patrick, Ballouz, Ronald-Louis, Jacobson, Seth A., Scheeres, Daniel J., Walsh, Kevin, Barnouin, Olivier, Daly, R. Terik, Palmer, Eric, Pajola, Maurizio, Lucchetti, Alice, Tusberti, Filippo, DeMartini, Joseph V., Ferrari, Fabio, Meyer, Alex J., Raducan, Sabina D., Sánchez, Paul
We explore binary asteroid formation by spin-up and rotational disruption considering the NASA DART mission's encounter with the Didymos-Dimorphos binary, which was the first small binary visited by a spacecraft. Using a suite of $N$-body simulations
Externí odkaz:
http://arxiv.org/abs/2401.09269