Search

We introduce LongSkywork, a long-context Large Language Model (LLM) capable of processing up to 200,000 tokens. We provide a training recipe for efficiently extending context length of LLMs. We identify that the critical element in enhancing long-context processing capability is to incorporate a long-context SFT stage following the standard SFT stage. A mere 200 iterations can convert the standard SFT model into a long-context model. To reduce the effort in collecting and annotating data for long-context language modeling, we develop two novel methods for creating synthetic data. These methods are applied during the continual pretraining phase as well as the Supervised Fine-Tuning (SFT) phase, greatly enhancing the training efficiency of our long-context LLMs. Our findings suggest that synthetic long-context SFT data can surpass the performance of data curated by humans to some extent. LongSkywork achieves outstanding performance on a variety of long-context benchmarks. In the Needle test, a benchmark for long-context information retrieval, our models achieved perfect accuracy across multiple context spans. Moreover, in realistic application scenarios, LongSkywork-13B demonstrates performance on par with Claude2.1, the leading long-context model, underscoring the effectiveness of our proposed methods.

Nonreciprocal charge transport in heterostructural superconductors exhibits appealing quantum physical phenomena and holds the promising potential for superconducting circuits applications. Realizing a nonreciprocity is, however, fundamentally and technologically challenging, as it requires a material structure without a centre of inversion, which is scarce among superconducting materials. Here, we report an evidence of helical superconductivity, in which the Rashba spin-orbit coupling induces momentum-dependent superconducting gap in the inversion symmetry breaking heterointerface superconductor consisting of Mott insulating Ti$_2$O$_3$ and polar semiconducting GaN. Remarkably, the nonlinear responses emerge in the superconducting transition regime, when the magnetic field is precisely aligned in-plane orientations perpendicular to the applied current. In particular, the observed nonreciprocal supercurrent is extremely sensitive to the direction of the magnetic field for 0.5 degree, suggestive of a crossover from a symmetry breaking state to a symmetric one. Our finding not only unveils the underlying rich physical properties in heterointerface superconductors, but also provides an exciting opportunity for the development of novel mesoscopic superconducting devices.

In recent years, analog circuits have received extensive attention and are widely used in many emerging applications. The high demand for analog circuits necessitates shorter circuit design cycles. To achieve the desired performance and specifications, various geometrical symmetry constraints must be carefully considered during the analog layout process. However, the manual labeling of these constraints by experienced analog engineers is a laborious and time-consuming process. To handle the costly runtime issue, we propose a graph-based learning framework to automatically extract symmetric constraints in analog circuit layout. The proposed framework leverages the connection characteristics of circuits and the devices' information to learn the general rules of symmetric constraints, which effectively facilitates the extraction of device-level constraints on circuit netlists. The experimental results demonstrate that compared to state-of-the-art symmetric constraint detection approaches, our framework achieves higher accuracy and F1-score., Comment: 11 pages,10 figures, 6 tables, 1 algorithm

Using ultrafast broad-band transient absorption (TA) spectroscopy of photo-excited MAPbBr3 thin films with probe continua in the visible and the mid-to-deep-UV ranges, we capture the ultrafast gap renormalization at the fundamental gap situated at the R symmetry point of the Brillouin Zone (BZ) and a higher energy gap at the M point. Global Lifetime analysis, Lifetime density distribution and spectral trace fitting analysis are applied to extract quantitative information. Our work confirms the similarity of the energy gap renormalization at both symmetry points, which rises within the instrument response function (IRF, ~250 fs) and decays in ~400-600 fs times, and an energy red-shift of ~90-150 meV. The ability to monitor different high symmetry points in photoexcited perovskites opens exciting prospects into the characterization of materials, which can be extended to a larger class of materials., Comment: 16 pages, 4 figures

As commonly-used methods for debiasing natural language understanding (NLU) models, dataset refinement approaches heavily rely on manual data analysis, and thus maybe unable to cover all the potential biased features. In this paper, we propose IBADR, an Iterative Bias-Aware Dataset Refinement framework, which debiases NLU models without predefining biased features. We maintain an iteratively expanded sample pool. Specifically, at each iteration, we first train a shallow model to quantify the bias degree of samples in the pool. Then, we pair each sample with a bias indicator representing its bias degree, and use these extended samples to train a sample generator. In this way, this generator can effectively learn the correspondence relationship between bias indicators and samples. Furthermore, we employ the generator to produce pseudo samples with fewer biased features by feeding specific bias indicators. Finally, we incorporate the generated pseudo samples into the pool. Experimental results and in-depth analyses on two NLU tasks show that IBADR not only significantly outperforms existing dataset refinement approaches, achieving SOTA, but also is compatible with model-centric methods., Comment: EMNLP2023 main conference

In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3.2 trillion tokens drawn from both English and Chinese texts. This bilingual foundation model is the most extensively trained and openly published LLMs of comparable size to date. We introduce a two-stage training methodology using a segmented corpus, targeting general purpose training and then domain-specific enhancement training, respectively. We show that our model not only excels on popular benchmarks, but also achieves \emph{state of the art} performance in Chinese language modeling on diverse domains. Furthermore, we propose a novel leakage detection method, demonstrating that test data contamination is a pressing issue warranting further investigation by the LLM community. To spur future research, we release Skywork-13B along with checkpoints obtained during intermediate stages of the training process. We are also releasing part of our SkyPile corpus, a collection of over 150 billion tokens of web text, which is the largest high quality open Chinese pre-training corpus to date. We hope Skywork-13B and our open corpus will serve as a valuable open-source resource to democratize access to high-quality LLMs.

Large language models (LLMs) have shown great potential to solve varieties of natural language processing (NLP) tasks, including mathematical reasoning. In this work, we present SkyMath, a large language model for mathematics with 13 billion parameters. By applying self-compare fine-tuning, we have enhanced mathematical reasoning abilities of Skywork-13B-Base remarkably. On GSM8K, SkyMath outperforms all known open-source models of similar size and has established a new SOTA performance.

Current Transformer-based natural language understanding (NLU) models heavily rely on dataset biases, while failing to handle real-world out-of-distribution (OOD) instances. Many methods have been proposed to deal with this issue, but they ignore the fact that the features learned in different layers of Transformer-based NLU models are different. In this paper, we first conduct preliminary studies to obtain two conclusions: 1) both low- and high-layer sentence representations encode common biased features during training; 2) the low-layer sentence representations encode fewer unbiased features than the highlayer ones. Based on these conclusions, we propose a simple yet effective self-debiasing framework for Transformer-based NLU models. Concretely, we first stack a classifier on a selected low layer. Then, we introduce a residual connection that feeds the low-layer sentence representation to the top-layer classifier. In this way, the top-layer sentence representation will be trained to ignore the common biased features encoded by the low-layer sentence representation and focus on task-relevant unbiased features. During inference, we remove the residual connection and directly use the top-layer sentence representation to make predictions. Extensive experiments and indepth analyses on NLU tasks show that our framework performs better than several competitive baselines, achieving a new SOTA on all OOD test sets.

Quantum Griffiths singularity (QGS), which is closely correlated with the quenched disorder, is characterized by the divergence of the dynamical critical exponent and the presence of activated scaling behavior. Typically such a quantum phenomenon is rather rare and only observed in extremely low temperatures. Here we report the experimental observation of a robust QGS in nitride thin films, NbN, which survives in a rather high temperature range. The electrical transport propertied were measured under the magnetic field up to 12 T. The field induced superconductor-metal transitions were observed with the continuously changed transition points with the decrease of temperature. The dynamical critical exponent based on the conventional power-law scaling reveals a divergent trend when approaching the the low temperature limit. Moreover, the temperature and field dependence of sheet resistance can be described by the activated scaling analysis in the temperature region up to 1.6 K $\leq T \leq$ 4.0 K. We argue that the robustness of QGS in the present system originates from the Pauli paramagnetic effect due to the strong coupling between the magnetic field and the spin degree of freedom., Comment: 6 pages, 4 figures

Superconductivity and the normal-state properties of NbN films can be tuned in a wide range, supplying a suitable platform to investigate the systematical evolution of the superconducting performances. Herein, we report the upper critical field of NbN films in both the vertical ($B\perp$ film) and parallel ($B\parallel$ film) orientations over a wide temperature range. Eight samples with the superconducting critical temperature $T_c$ ranging from 2.5 K to 9.8 K are studied. Meanwhile, the normal-state resistivity is tuned by more than six times by changing the conditions of the film growth. It is found that the magnitudes of the upper critical field in both field directions ($B_{c2}^{\perp}$ and $B_{c2}^{\parallel}$) exceed the paramagnetic limiting field $B_p$. The temperature dependent $B_{c2}^{\perp}$ can be described by the extended Werthamer--Helfand--Hohenberg (WHH) model considering the Pauli spin paramagnetism. Meanwhile, the $B_{c2}^{\parallel}$-$T$ data shows the feature of two-dimensional superconductivity in the temperature range near $T_c$. The evolution of the obtained Maki parameter with other parameters, such as the slope of the upper critical field near $T_c$ and the normal-state resistivity, are discussed to reveal the characteristics of the Pauli paramagnetic effect in this system., Comment: 7 pages, 6 figures

The emergence of quantum metallic state marked by a saturating finite electrical resistance in the zero-temperature limit in a variety of two-dimensional superconductors injects an exciting momentum to the realm of heterostructure superconductivity. Despite much research efforts over last few decades, there is not yet a general consensus on the nature of this unexpected quantum metal. Here, we report the observation of a unique quantum metallic state within the hallmark of Bose-metal in the titanium sesquioxide heterointerface superconductor Ti$_2$O$_3$/GaN. Remarkably, the quantum bosonic metallic state continuously tuned by a magnetic field in the vicinity of the two-dimensional superconductivity-metal transition persists in the normal phase, indicating the existence of composite bosons formed by electron Cooper pairs even in the normal phase. Our findings provide a distinct evidence for electron pairing in the normal phase of heterointerface superconductors, and shed fresh light on the pairing nature underlying heterointerface superconductivity., Comment: 12 pages, 4 figures

As the first session-level Chinese dataset, CHASE contains two separate parts, i.e., 2,003 sessions manually constructed from scratch (CHASE-C), and 3,456 sessions translated from English SParC (CHASE-T). We find the two parts are highly discrepant and incompatible as training and evaluation data. In this work, we present SeSQL, yet another large-scale session-level text-to-SQL dataset in Chinese, consisting of 5,028 sessions all manually constructed from scratch. In order to guarantee data quality, we adopt an iterative annotation workflow to facilitate intense and in-time review of previous-round natural language (NL) questions and SQL queries. Moreover, by completing all context-dependent NL questions, we obtain 27,012 context-independent question/SQL pairs, allowing SeSQL to be used as the largest dataset for single-round multi-DB text-to-SQL parsing. We conduct benchmark session-level text-to-SQL parsing experiments on SeSQL by employing three competitive session-level parsers, and present detailed analysis., Comment: 12 pages,4 figures

While pre-trained language models (LMs) have brought great improvements in many NLP tasks, there is increasing attention to explore capabilities of LMs and interpret their predictions. However, existing works usually focus only on a certain capability with some downstream tasks. There is a lack of datasets for directly evaluating the masked word prediction performance and the interpretability of pre-trained LMs. To fill in the gap, we propose a novel evaluation benchmark providing with both English and Chinese annotated data. It tests LMs abilities in multiple dimensions, i.e., grammar, semantics, knowledge, reasoning and computation. In addition, it provides carefully annotated token-level rationales that satisfy sufficiency and compactness. It contains perturbed instances for each original instance, so as to use the rationale consistency under perturbations as the metric for faithfulness, a perspective of interpretability. We conduct experiments on several widely-used pre-trained LMs. The results show that they perform very poorly on the dimensions of knowledge and computation. And their plausibility in all dimensions is far from satisfactory, especially when the rationale is short. In addition, the pre-trained LMs we evaluated are not robust on syntax-aware data. We will release this evaluation benchmark at \url{http://xyz}, and hope it can facilitate the research progress of pre-trained LMs., Comment: 10 pages, 2 figures

While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel benchmark to evaluate the interpretability of both neural models and saliency methods. This benchmark covers three representative NLP tasks: sentiment analysis, textual similarity and reading comprehension, each provided with both English and Chinese annotated data. In order to precisely evaluate the interpretability, we provide token-level rationales that are carefully annotated to be sufficient, compact and comprehensive. We also design a new metric, i.e., the consistency between the rationales before and after perturbations, to uniformly evaluate the interpretability on different types of tasks. Based on this benchmark, we conduct experiments on three typical models with three saliency methods, and unveil their strengths and weakness in terms of interpretability. We will release this benchmark https://www.luge.ai/#/luge/task/taskDetail?taskId=15 and hope it can facilitate the research in building trustworthy systems.

Grammar-based parsers have achieved high performance in the cross-domain text-to-SQL parsing task, but suffer from low decoding efficiency due to the much larger number of actions for grammar selection than that of tokens in SQL queries. Meanwhile, how to better align SQL clauses and question segments has been a key challenge for parsing performance. Therefore, this paper proposes clause-level parallel decoding and alignment loss to enhance two high-performance grammar-based parsers, i.e., RATSQL and LGESQL. Experimental results of two parsers show that our method obtains consistent improvements both in accuracy and decoding speed.

Broken symmetries play a fundamental role in superconductivity and influence many of its properties in a profound way. Understanding these symmetry breaking states is essential to elucidate the various exotic quantum behaviors in non-trivial superconductors. Here, we report an experimental observation of spontaneous rotational symmetry breaking of superconductivity at the heterointerface of amorphous (a)-YAlO$_3$/KTaO$_3$(111) with a superconducting transition temperature of 1.86 K. Both the magnetoresistance and superconducting critical field in an in-plane field manifest striking twofold symmetric oscillations deep inside the superconducting state, whereas the anisotropy vanishes in the normal state, demonstrating that it is an intrinsic property of the superconducting phase. We attribute this behavior to the mixed-parity superconducting state, which is an admixture of \emph{s}-wave and \emph{p}-wave pairing components induced by strong spin-orbit coupling inherent to inversion symmetry breaking at the heterointerface of a-YAlO$_3$/KTaO$_3$. Our work suggests an unconventional nature of the underlying pairing interaction in the KTaO$_3$ heterointerface superconductors, and brings a new broad of perspective on understanding non-trivial superconducting properties at the artificial heterointerfaces., Comment: 9 pages, 4 figures