Warning: this paper contains model outputs exhibiting offensiveness and biases.Large language models (LLMs) have achieved impressive performance on various natural language generation tasks. Nonetheless, they suffer from generating negative and harmful contents that are biased against certain demographic groups (e.g., female), raising severe fairness concerns. As remedies, prior works intervened the generation by removing attitude or demographic information, inevitably degrading the generation quality and resulting in notable fairness-fluency trade-offs. However, it is still under-explored to what extent the fluency has to be affected in order to achieve a desired level of fairness. In this work, we conduct the first formal study from an information-theoretic perspective. We show that previous approaches are excessive for debiasing and propose LIDAO, a general framework to debias a (L)LM at a better fluency provably. We further robustify LIDAO in adversarial scenarios, where a carefully-crafted prompt may stimulate LLMs exhibiting instruction-following abilities to generate texts with fairness issue appears only when the prompt is also taken into account. Experiments on three LMs ranging from 0.7B to 7B parameters demonstrate the superiority of our method.
Transferred graphene provides a promising III-nitride semiconductor epitaxial platform for fabricating multifunctional devices beyond the limitation of conventional substrates. Despite its tremendous fundamental and technological importance, it remains an open question on which kind of epitaxy is preferred for single-crystal III-nitrides. Popular answers to this include the remote epitaxy where the III-nitride/graphene interface is coupled by nonchemical bonds, and the quasi-van der Waals epitaxy (quasi-vdWe) where the interface is mainly coupled by covalent bonds. Here, we show the preferred one on wet-transferred graphene is quasi-vdWe. Using aluminum nitride (AlN), a strong polar III-nitride, as an example, we demonstrate that the remote interaction from the graphene/AlN template can inhibit out-of-plane lattice inversion other than in-plane lattice twist of the nuclei, resulting in a polycrystalline AlN film. In contrast, quasi-vdWe always leads to single-crystal film. By answering this long-standing controversy, this work could facilitate the development of III-nitride semiconductor devices on two-dimensional materials such as graphene.
Understanding thermal transport across metal/semiconductor interfaces is crucial for the heat dissipation of electronics. The dominant heat carriers in non-metals, phonons, are thought to transport elastically across most interfaces, except for a few extreme cases where the two materials that formed the interface are highly dissimilar with a large difference in Debye temperature. In this work, we show that even for two materials with similar Debye temperatures (Al/Si, Al/GaN), a substantial portion of phonons will transport inelastically across their interfaces at high temperatures, significantly enhancing interface thermal conductance. Moreover, we find that interface sharpness strongly affects phonon transport process. For atomically sharp interfaces, phonons are allowed to transport inelastically and interface thermal conductance linearly increases at high temperatures. With a diffuse interface, inelastic phonon transport diminishes. Our results provide new insights on phonon transport across interfaces and open up opportunities for engineering interface thermal conductance specifically for materials of relevance to microelectronics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.