Search

We present a novel methodology for in-situ Transmission Kikuchi Diffraction (TKD) nano-tensile testing that enables nanoscale characterization of the evolution of complex plasticity mechanisms. By integrating a modified in-situ Scanning Electron Microscope (SEM) nanoindenter with a microscale push-to-pull device and a conventional Electron Backscatter Diffraction (EBSD) detector, we achieved TKD measurements at high spatial resolution during mechanical deformation. A dedicated Focused Ion Beam (FIB) procedure was developed for site-specific specimen fabrication, including lift-out, thinning, and shaping into a dog-bone geometry. The methodology was demonstrated on two case studies: (i) a metastable $\beta$-Ti single crystal, on which we quantified the initiation and evolution of nanoscale twinning and stress-induced martensitic transformation, and (ii) a $CuAl/Al_2O_3$ nanolaminate, which showed nanoscale plasticity and twinning/detwinning in a complex microstructure. Overall, this approach provides a robust alternative to in-situ EBSD and Transmission Electron Microscopy (TEM) testing, facilitating detailed analysis of deformation mechanisms at the nanoscale., Comment: 12 pages, 5 figures, submitted for publication

We introduce Planning-guided Retrieval Augmented Generation (Plan$\times$RAG), a novel framework that augments the \emph{retrieve-then-reason} paradigm of existing RAG frameworks to \emph{plan-then-retrieve}. Plan$\times$RAG formulates a reasoning plan as a directed acyclic graph (DAG), decomposing queries into interrelated atomic sub-queries. Answer generation follows the DAG structure, allowing significant gains in efficiency through parallelized retrieval and generation. While state-of-the-art RAG solutions require extensive data generation and fine-tuning of language models (LMs), Plan$\times$RAG incorporates frozen LMs as plug-and-play experts to generate high-quality answers. Compared to existing RAG solutions, Plan$\times$RAG demonstrates significant improvements in reducing hallucinations and bolstering attribution due to its structured sub-query decomposition. Overall, Plan$\times$RAG offers a new perspective on integrating external knowledge in LMs while ensuring attribution by design, contributing towards more reliable LM-based systems., Comment: 22 pages, preprint

Four-dimensional scanning transmission electron microscopy (4D-STEM) is a powerful tool that allows for the simultaneous acquisition of spatial and diffraction information, driven by recent advancements in direct electron detector technology. Although 4D-STEM has been predominantly developed for and used in conventional TEM and STEM, efforts are being made to implement the technique in scanning electron microscopy (SEM). In this paper, we push the boundaries of 4D-STEM in SEM and extend its capabilities in three key aspects: (1) faster acquisition rate with reduced data size, (2) higher angular resolution, and (3) application to various materials including conventional alloys and focused ion beam (FIB) lamella. Specifically, operating the MiniPIX Timepix3 detector in the event-driven mode significantly improves the acquisition rate by a factor of a few tenths compared to conventional frame-based mode, thereby opening up possibilities for integrating 4D-STEM into various in situ SEM testing. Furthermore, with a novel stage-detector geometry, a camera length of 160 mm is achieved which improves the angular resolution amplifying its utility, for example, magnetic or electric field imaging. Lastly, we successfully imaged a nanostructured platinum-copper thin film with a grain size of 16 nm and a thickness of 20 nm, and identified annealing twins in FIB-prepared polycrystalline copper using virtual darkfield imaging and orientation mapping. This work demonstrates the potential of synergetic combination of 4D-STEM with in situ experiments, and broadening its applications across a wide range of materials.

An equimolar NiCoFeCrGa high entropy alloy having dual-phase homogeneous components was studied, where the constituent phases exhibit distinct mechanical properties. Micropillars with various diameters were created from two differently heat treated samples, then they were compressed at slow strain rates, that revealed the material's limited sensitivity to size. On the other hand, increased strain rate sensitivity at high deformation speeds was observed, that differs substantially depending on the phase composition of the specimen. Dislocations within the two phases were studied by high resolution transmission electron microscopy and high angular resolution electron backscatter diffraction. The performed chemical analysis confirmed that slow cooling during casting create Cr-rich precipitates, that have significant impact on the global strength of the material.

Extreme Classification (XC) aims to map a query to the most relevant documents from a very large document set. XC algorithms used in real-world applications learn this mapping from datasets curated from implicit feedback, such as user clicks. However, these datasets inevitably suffer from missing labels. In this work, we observe that systematic missing labels lead to missing knowledge, which is critical for accurately modelling relevance between queries and documents. We formally show that this absence of knowledge cannot be recovered using existing methods such as propensity weighting and data imputation strategies that solely rely on the training dataset. While LLMs provide an attractive solution to augment the missing knowledge, leveraging them in applications with low latency requirements and large document sets is challenging. To incorporate missing knowledge at scale, we propose SKIM (Scalable Knowledge Infusion for Missing Labels), an algorithm that leverages a combination of small LM and abundant unstructured meta-data to effectively mitigate the missing label problem. We show the efficacy of our method on large-scale public datasets through exhaustive unbiased evaluation ranging from human annotations to simulations inspired from industrial settings. SKIM outperforms existing methods on Recall@100 by more than 10 absolute points. Additionally, SKIM scales to proprietary query-ad retrieval datasets containing 10 million documents, outperforming contemporary methods by 12% in offline evaluation and increased ad click-yield by 1.23% in an online A/B test conducted on a popular search engine. We release our code, prompts, trained XC models and finetuned SLMs at: https://github.com/bicycleman15/skim, Comment: Preprint, 23 pages

For text-based AI systems to interact in the real world, causal reasoning is an essential skill. Since interventional data is costly to generate, we study to what extent an agent can learn causal reasoning from passive data. Specifically, we consider an axiomatic training setup where an agent learns from multiple demonstrations of a causal axiom (or rule), rather than incorporating the axiom as an inductive bias or inferring it from data values. A key question is whether the agent would learn to generalize from the axiom demonstrations to new scenarios. For example, if a transformer model is trained on demonstrations of the causal transitivity axiom over small graphs, would it generalize to applying the transitivity axiom over large graphs? Our results, based on a novel axiomatic training scheme, indicate that such generalization is possible. We consider the task of inferring whether a variable causes another variable, given a causal graph structure. We find that a 67 million parameter transformer model, when trained on linear causal chains (along with some noisy variations) can generalize well to new kinds of graphs, including longer causal chains, causal chains with reversed order, and graphs with branching; even when it is not explicitly trained for such settings. Our model performs at par (or even better) than many larger language models such as GPT-4, Gemini Pro, and Phi-3. Overall, our axiomatic training framework provides a new paradigm of learning causal reasoning from passive data that can be used to learn arbitrary axioms, as long as sufficient demonstrations can be generated.

Most complex systems are nonlinear, relying on emergent behavior from interacting subsystems, often characterized by oscillatory dynamics. Collective oscillatory behavior is essential for the proper functioning of many real world systems. Complex networks have proven efficient in elucidating the topological structures of both natural and artificial systems and describing diverse processes occurring within them. Recent advancements have significantly enhanced our understanding of emergent dynamics in complex networks. Among various processes, a substantial body of work explores the dynamical robustness of complex networks, their ability to withstand degradation in network constituents while maintaining collective oscillatory dynamics. Many physical and biological systems experience a decline in dynamic activities due to natural or environmental factors. The impact of such damages on network performance can be significant, and the system's robustness indicates its capability to maintain functionality despite dynamic changes, often termed aging. This review provides a comprehensive overview of notable research examining how networks sustain global oscillation despite increasing inactive dynamical units. We present contemporary research dedicated to the theoretical understanding and enhancement mechanisms of dynamical robustness in complex networks. Our focus includes various network structures and coupling functions, elucidating the persistence of networked systems. We cover system characteristics from heterogeneity in network connectivity to heterogeneity in dynamical units. Finally, we discuss challenges in this field and open areas for future studies., Comment: 52 pages, 33 figures

Given an input query, a recommendation model is trained using user feedback data (e.g., click data) to output a ranked list of items. In real-world systems, besides accuracy, an important consideration for a new model is novelty of its top-k recommendations w.r.t. an existing deployed model. However, novelty of top-k items is a difficult goal to optimize a model for, since it involves a non-differentiable sorting operation on the model's predictions. Moreover, novel items, by definition, do not have any user feedback data. Given the semantic capabilities of large language models, we address these problems using a reinforcement learning (RL) formulation where large language models provide feedback for the novel items. However, given millions of candidate items, the sample complexity of a standard RL algorithm can be prohibitively high. To reduce sample complexity, we reduce the top-k list reward to a set of item-wise rewards and reformulate the state space to consist of tuples such that the action space is reduced to a binary decision; and show that this reformulation results in a significantly lower complexity when the number of items is large. We evaluate the proposed algorithm on improving novelty for a query-ad recommendation task on a large-scale search engine. Compared to supervised finetuning on recent pairs, the proposed RL-based algorithm leads to significant novelty gains with minimal loss in recall. We obtain similar results on the ORCAS query-webpage matching dataset and a product recommendation dataset based on Amazon reviews., Comment: Accepted at KDD 2024

Given a task in the form of a basic description and its training examples, prompt optimization is the problem of synthesizing the given information into a text prompt for a large language model (LLM). Humans solve this problem by also considering the different facets that define a task (e.g., counter-examples, explanations, analogies) and including them in the prompt. However, it is unclear whether existing algorithmic approaches, based on iteratively editing a given prompt or automatically selecting a few in-context examples, can cover the multiple facets required to solve a complex task. In this work, we view prompt optimization as that of learning multiple facets of a task from a set of training examples. We identify and exploit structure in the prompt optimization problem -- first, we find that prompts can be broken down into loosely coupled semantic sections that have a relatively independent effect on the prompt's performance; second, we cluster the input space and use clustered batches so that the optimization procedure can learn the different facets of a task across batches. The resulting algorithm, UniPrompt, consists of a generative model to generate initial candidates for each prompt section; and a feedback mechanism that aggregates suggested edits from multiple mini-batches into a conceptual description for the section. Empirical evaluation on multiple datasets and a real-world task shows that prompts generated using UniPrompt obtain higher accuracy than human-tuned prompts and those from state-of-the-art methods. In particular, our algorithm can generate long, complex prompts that existing methods are unable to generate. Code for UniPrompt will be available at \url{https://aka.ms/uniprompt}.

This paper presents a comparative analysis of total cost of ownership (TCO) and performance between domain-adapted large language models (LLM) and state-of-the-art (SoTA) LLMs , with a particular emphasis on tasks related to coding assistance for chip design. We examine the TCO and performance metrics of a domain-adaptive LLM, ChipNeMo, against two leading LLMs, Claude 3 Opus and ChatGPT-4 Turbo, to assess their efficacy in chip design coding generation. Through a detailed evaluation of the accuracy of the model, training methodologies, and operational expenditures, this study aims to provide stakeholders with critical information to select the most economically viable and performance-efficient solutions for their specific needs. Our results underscore the benefits of employing domain-adapted models, such as ChipNeMo, that demonstrate improved performance at significantly reduced costs compared to their general-purpose counterparts. In particular, we reveal the potential of domain-adapted LLMs to decrease TCO by approximately 90%-95%, with the cost advantages becoming increasingly evident as the deployment scale expands. With expansion of deployment, the cost benefits of ChipNeMo become more pronounced, making domain-adaptive LLMs an attractive option for organizations with substantial coding needs supported by LLMs, Comment: Paper accepted in IEEE-ACM conference: 2024 IEEE LLM-Aided Design Workshop (LAD)

The effective management of brain tumors relies on precise typing, subtyping, and grading. This study advances patient care with findings from rigorous multiple instance learning experimentations across various feature extractors and aggregators in brain tumor histopathology. It establishes new performance benchmarks in glioma subtype classification across multiple datasets, including a novel dataset focused on the Indian demographic (IPD- Brain), providing a valuable resource for existing research. Using a ResNet-50, pretrained on histopathology datasets for feature extraction, combined with the Double-Tier Feature Distillation (DTFD) feature aggregator, our approach achieves state-of-the-art AUCs of 88.08 on IPD-Brain and 95.81 on the TCGA-Brain dataset, respectively, for three-way glioma subtype classification. Moreover, it establishes new benchmarks in grading and detecting IHC molecular biomarkers (IDH1R132H, TP53, ATRX, Ki-67) through H&E stained whole slide images for the IPD-Brain dataset. The work also highlights a significant correlation between the model decision-making processes and the diagnostic reasoning of pathologists, underscoring its capability to mimic professional diagnostic procedures.

Recent work shows that in-context learning and optimization of in-context examples (ICE) can significantly improve the accuracy of large language models (LLMs) on a wide range of tasks, leading to an apparent consensus that ICE optimization is crucial for better performance. However, most of these studies assume a fixed or no instruction provided in the prompt. We challenge this consensus by investigating the necessity of optimizing ICE when task-specific instructions are provided and find that there are many tasks for which it yields diminishing returns. In particular, using a diverse set of tasks and a systematically created instruction set with gradually added details, we find that as the prompt instruction becomes more detailed, the returns on ICE optimization diminish. To characterize this behavior, we introduce a task-specific metric called Normalized Invariability to Choice of Examples (NICE) that quantifies the learnability of tasks from a given instruction, and provides a heuristic to help decide whether to optimize instructions or ICE for a new task. Given a task, the proposed metric can reliably predict the utility of optimizing ICE compared to using random ICE. Our code is available at https://github.com/microsoft/nice-icl., Comment: Accepted as a full paper (9 pages) at ACL 2024 (Main)

The mechanical performance of metallic metamaterials with 3-dimensional solid frames is typically a combination of the geometrical effect ("architecture") and the characteristic size effects of the base material ("microstructure"). In this study, for the first time, the temperature- and rate-dependent mechanical response of copper microlattices has been investigated. The microlattices were fabricated via a localized electrodeposition in liquid (LEL) process which enables high-precision additive manufacturing of metal at the micro-scale. The metal microlattices possess a unique microstructure with micron sized grains that are rich with randomly oriented growth twins and near-ideal nodal connectivity. Importantly, copper microlattices exhibited unique temperature (-150 and 25 degree C) and strain rate (0.001~100 s-1) dependent deformation behavior during in situ micromechanical testing. Systematic compression tests of fully dense copper micropillars, equivalent in diameter and length to the struts of the microlattice at comparable extreme loading conditions, allow us to investigate the intrinsic deformation mechanism of copper. Combined with the post-mortem microstructural analysis, substantial shifts in deformation mechanisms depending on the temperature and strain rate were revealed. On the one hand, at room temperature (25 degree C), dislocation slip based plastic deformation occurs and leads to a localized deformation of the micropillars. On the other hand, at cryogenic temperature (-150 degree C), mechanical twinning occurs and leads to relatively homogeneous deformation of the micropillars. Based on the intrinsic deformation mechanisms of copper, the temperature and strain rate dependent deformation behavior of microlattices could be explained.

Given a query and a document corpus, the information retrieval (IR) task is to output a ranked list of relevant documents. Combining large language models (LLMs) with embedding-based retrieval models, recent work shows promising results on the zero-shot retrieval problem, i.e., no access to labeled data from the target domain. Two such popular paradigms are generation-augmented retrieval or GAR (generate additional context for the query and then retrieve), and retrieval-augmented generation or RAG (retrieve relevant documents as context and then generate answers). The success of these paradigms hinges on (i) high-recall retrieval models, which are difficult to obtain in the zero-shot setting, and (ii) high-precision (re-)ranking models which typically need a good initialization. In this work, we propose a novel GAR-meets-RAG recurrence formulation that overcomes the challenges of existing paradigms. Our method iteratively improves retrieval (via GAR) and rewrite (via RAG) stages in the zero-shot setting. A key design principle is that the rewrite-retrieval stages improve the recall of the system and a final re-ranking stage improves the precision. We conduct extensive experiments on zero-shot passage retrieval benchmarks, BEIR and TREC-DL. Our method establishes a new state-of-the-art in the BEIR benchmark, outperforming previous best results in Recall@100 and nDCG@10 metrics on 6 out of 8 datasets, with up to 17% relative gains over the previous best., Comment: preprint

At the core of causal inference lies the challenge of determining reliable causal graphs solely based on observational data. Since the well-known backdoor criterion depends on the graph, any errors in the graph can propagate downstream to effect inference. In this work, we initially show that complete graph information is not necessary for causal effect inference; the topological order over graph variables (causal order) alone suffices. Further, given a node pair, causal order is easier to elicit from domain experts compared to graph edges since determining the existence of an edge can depend extensively on other variables. Interestingly, we find that the same principle holds for Large Language Models (LLMs) such as GPT-3.5-turbo and GPT-4, motivating an automated method to obtain causal order (and hence causal effect) with LLMs acting as virtual domain experts. To this end, we employ different prompting strategies and contextual cues to propose a robust technique of obtaining causal order from LLMs. Acknowledging LLMs' limitations, we also study possible techniques to integrate LLMs with established causal discovery algorithms, including constraint-based and score-based methods, to enhance their performance. Extensive experiments demonstrate that our approach significantly improves causal ordering accuracy as compared to discovery algorithms, highlighting the potential of LLMs to enhance causal inference across diverse fields.

Causal explanations of the predictions of NLP systems are essential to ensure safety and establish trust. Yet, existing methods often fall short of explaining model predictions effectively or efficiently and are often model-specific. In this paper, we address model-agnostic explanations, proposing two approaches for counterfactual (CF) approximation. The first approach is CF generation, where a large language model (LLM) is prompted to change a specific text concept while keeping confounding concepts unchanged. While this approach is demonstrated to be very effective, applying LLM at inference-time is costly. We hence present a second approach based on matching, and propose a method that is guided by an LLM at training-time and learns a dedicated embedding space. This space is faithful to a given causal graph and effectively serves to identify matches that approximate CFs. After showing theoretically that approximating CFs is required in order to construct faithful explanations, we benchmark our approaches and explain several models, including LLMs with billions of parameters. Our empirical results demonstrate the excellent performance of CF generation models as model-agnostic explainers. Moreover, our matching approach, which requires far less test-time resources, also provides effective explanations, surpassing many baselines. We also find that Top-K techniques universally improve every tested method. Finally, we showcase the potential of LLMs in constructing new benchmarks for model explanation and subsequently validate our conclusions. Our work illuminates new pathways for efficient and accurate approaches to interpreting NLP systems.