Search

Prompt serves as a crucial link in interacting with large language models (LLMs), widely impacting the accuracy and interpretability of model outputs. However, acquiring accurate and high-quality responses necessitates precise prompts, which inevitably pose significant risks of personal identifiable information (PII) leakage. Therefore, this paper proposes DePrompt, a desensitization protection and effectiveness evaluation framework for prompt, enabling users to safely and transparently utilize LLMs. Specifically, by leveraging large model fine-tuning techniques as the underlying privacy protection method, we integrate contextual attributes to define privacy types, achieving high-precision PII entity identification. Additionally, through the analysis of key features in prompt desensitization scenarios, we devise adversarial generative desensitization methods that retain important semantic content while disrupting the link between identifiers and privacy attributes. Furthermore, we present utility evaluation metrics for prompt to better gauge and balance privacy and usability. Our framework is adaptable to prompts and can be extended to text usability-dependent scenarios. Through comparison with benchmarks and other model methods, experimental evaluations demonstrate that our desensitized prompt exhibit superior privacy protection utility and model inference results.

Hysteretic switching of domain states is a salient character of all ferroic materials and the foundation for their multifunctional applications. Ferro-rotational order is emerging as a new type of ferroic order featuring structural rotations, but its controlled switching remains elusive due to its invariance under both time reversal and spatial inversion. Here, we demonstrate electrical switching of ferro-rotational domain states in nanometer-thick 1T-TaS$_2$ crystals in its charge-density-wave phases. Cooling from the high-symmetry phase to the ferro-rotational phase under an external electric field induces domain state switching and domain wall formation, realized in a simple two-terminal configuration using a volt-scale voltage. Although the electric field does not couple with the order due to symmetry mismatch, it drives domain wall propagation to give rise to reversible, durable, and nonvolatile isothermal state switching at room temperature. These results pave the path for manipulation of the ferro-rotational order and its nanoelectronic applications.

In this work, we report a novel design, one-transistor-one-inverter (1T1I), to satisfy high speed and low power on-chip training requirements. By leveraging doped HfO2 with ferroelectricity, a non-volatile inverter is successfully demonstrated, enabling desired continuous weight transition between negative and positive via the programmable threshold voltage (VTH) of ferroelectric field-effect transistors (FeFETs). Compared with commonly used designs with the similar function, 1T1I uniquely achieves pure on-chip-based weight transition at an optimized working current without relying on assistance from off-chip calculation units for signed-weight comparison, facilitating high-speed training at low power consumption. Further improvements in linearity and training speed can be obtained via a two-transistor-one-inverter (2T1I) design. Overall, focusing on energy and time efficiencies, this work provides a valuable design strategy for future FeFET-based computing-in-memory (CiM).

The charge-density wave (CDW) phase is often accompanied by the condensation of a soft acoustic phonon mode, giving rise to lattice distortion and charge density modulation. This picture was challenged for the recently discovered kagome metal CsV$_3$Sb$_5$, based on the evidence of absence of soft phonons. Here we report the observation of Raman-active CDW amplitude modes in this material, which are collective excitations typically thought to emerge out of frozen soft phonons. The amplitude modes strongly hybridize with other superlattice modes, imparting them with clear temperature-dependent frequency shift and broadening, rarely seen in other known CDW materials. Both the mode mixing and the large amplitude mode frequencies suggest that the CDW exhibits the character of strong electron-phonon coupling, a regime in which acoustic phonon softening can cease to exist. The observation of amplitude modes in the absence of soft phonons highlights the unconventional nature of the CDW in CsV$_3$Sb$_5$.

Combinatorial Optimization (CO) has been a long-standing challenging research topic featured by its NP-hard nature. Traditionally such problems are approximately solved with heuristic algorithms which are usually fast but may sacrifice the solution quality. Currently, machine learning for combinatorial optimization (MLCO) has become a trending research topic, but most existing MLCO methods treat CO as a single-level optimization by directly learning the end-to-end solutions, which are hard to scale up and mostly limited by the capacity of ML models given the high complexity of CO. In this paper, we propose a hybrid approach to combine the best of the two worlds, in which a bi-level framework is developed with an upper-level learning method to optimize the graph (e.g. add, delete or modify edges in a graph), fused with a lower-level heuristic algorithm solving on the optimized graph. Such a bi-level approach simplifies the learning on the original hard CO and can effectively mitigate the demand for model capacity. The experiments and results on several popular CO problems like Directed Acyclic Graph scheduling, Graph Edit Distance and Hamiltonian Cycle Problem show its effectiveness over manually designed heuristics and single-level learning methods., Comment: NeurIPS 2021. Code at https://github.com/Thinklab-SJTU/PPO-BiHyb

Scheduling computational tasks represented by directed acyclic graphs (DAGs) is challenging because of its complexity. Conventional scheduling algorithms rely heavily on simple heuristics such as shortest job first (SJF) and critical path (CP), and are often lacking in scheduling quality. In this paper, we present a novel learning-based approach to scheduling DAG tasks. The algorithm employs a reinforcement learning agent to iteratively add directed edges to the DAG, one at a time, to enforce ordering (i.e., priorities of execution and resource allocation) of "tricky" job nodes. By doing so, the original DAG scheduling problem is dramatically reduced to a much simpler proxy problem, on which heuristic scheduling algorithms such as SJF and CP can be efficiently improved. Our approach can be easily applied to any existing heuristic scheduling algorithms. On the benchmark dataset of TPC-H, we show that our learning based approach can significantly improve over popular heuristic algorithms and consistently achieves the best performance among several methods under a variety of settings.

IrTe$_2$ with large spin-orbital coupling (SOC) shows a CDW-like first order structural phase transition from high-temperature trigonal phase to low-temperature monoclinic phase at 270 K, accompanying with a large jump in transport and magnetic measurement as well as in heat capacity. Here, the 3d element Ni has been doped into IrTe$_2$ by growing Ir$_{1-x}$Ni$_x$Te$_2$ single crystals. Both XRD and XPS results reveal that the Ni atoms have substituted for Ir, which is consistent with the calculation result. Like the CDW behaviour, the structural phase transition shows competition and coexistence with the superconductivity. The monoclinic phase transition has been suppressed gradually with the increase of the doping amount of Ni, at last giving rise to the stabilization of the trigonal phase with superconductivity. Within 0.1$\leq$x$\leq$0.2, Ir$_{1-x}$Ni$_x$Te$_2$ shows the superconductive behaviour with T$_c$ around 2.6K. The superconductivity shows anisotropy with dimensionless anisotropy parameter $\gamma$=$\xi_{//}$$/$$\xi_{\perp}$$\sim$ 2. Even Ni element shows ferromagnetic behaviour, Ir$_{1-x}$Ni$_x$Te$_2$ only shows weak paramagnetism, no ferromagnetic order is observed in it, which is coincident with the calculation result that their up and down spin density of states compensate each other well. In addition, for other 3d elements Fe, Co and Mn doped IrTe$_2$, only Ir$_{1-x}$Mn$_x$Te$_2$ owns magnetism with magnetic moment of 3.0$\mu$$_B$ to the supercell, theoretically.