Model misspecification analysis strategies, such as anomaly detection, model validation, and model comparison are a key component of scientific model development. Over the last few years, there has been a rapid rise in the use of simulation-based inference (SBI) techniques for Bayesian parameter estimation, applied to increasingly complex forward models. To move towards fully simulation-based analysis pipelines, however, there is an urgent need for a comprehensive simulation-based framework for model misspecification analysis. In this work, we provide a solid and flexible foundation for a wide range of model discrepancy analysis tasks, using distortion-driven model misspecification tests. From a theoretical perspective, we introduce the statistical framework built around performing many hypothesis tests for distortions of the simulation model. We also make explicit analytic connections to classical techniques: anomaly detection, model validation, and goodness-of-fit residual analysis. Furthermore, we introduce an efficient self-calibrating training algorithm that is useful for practitioners. We demonstrate the performance of the framework in multiple scenarios, making the connection to classical results where they are valid. Finally, we show how to conduct such a distortion-driven model misspecification test for real gravitational wave data, specifically on the event GW150914.
Studies have underscored how, regardless of the recent breakthrough and swift advances in AI research, even state-of-the-art Large Language models (LLMs) continue to struggle when performing logical and mathematical reasoning. The results seem to suggest that LLMs still work as (highly advanced) data pattern identifiers, scoring poorly when attempting to generalise and solve reasoning problems the models have never previously seen or that are not close to samples presented in their training data. To address this compelling concern, this paper makes use of the notion of critical questions from the literature on argumentation theory, focusing in particular on Toulmin's model of argumentation. We show that employing these critical questions can improve the reasoning capabilities of LLMs. By probing the rationale behind the models' reasoning process, the LLM can assess whether some logical mistake is occurring and correct it before providing the final reply to the user prompt. The underlying idea is drawn from the gold standard of any valid argumentative procedure: the conclusion is valid if it is entailed by accepted premises. Or, to paraphrase such Aristotelian principle in a real-world approximation, characterised by incomplete information and presumptive logic, the conclusion is valid if not proved otherwise. This approach successfully steers the models' output through a reasoning pipeline, resulting in better performance against the baseline and its Chain-of-Thought (CoT) implementation. To this end, an extensive evaluation of the proposed approach on the MT-Bench Reasoning and Math tasks across a range of LLMs is provided.
Vision-Language Models (VLMs), such as CLIP, have already seen widespread applications. Researchers actively engage in further fine-tuning VLMs in safety-critical domains. In these domains, prediction rationality is crucial: the prediction should be correct and based on valid evidence. Yet, for VLMs, the impact of fine-tuning on prediction rationality is seldomly investigated. To study this problem, we proposed two new metrics called Prediction Trustworthiness and Inference Reliability. We conducted extensive experiments on various settings and observed some interesting phenomena. On the one hand, we found that the well-adopted fine-tuning methods led to more correct predictions based on invalid evidence. This potentially undermines the trustworthiness of correct predictions from fine-tuned VLMs. On the other hand, having identified valid evidence of target objects, fine-tuned VLMs were more likely to make correct predictions. Moreover, the findings are also consistent under distributional shifts and across various experimental settings. We hope our research offer fresh insights to VLM fine-tuning.
Learning the Individual Treatment Effect (ITE) is essential for personalized decision-making, yet causal inference has traditionally focused on aggregated treatment effects. While integrating conformal prediction with causal inference can provide valid uncertainty quantification for ITEs, the resulting prediction intervals are often excessively wide, limiting their practical utility. To address this limitation, we introduce \underline{S}urrogate-assisted \underline{C}onformal \underline{I}nference for \underline{E}fficient I\underline{N}dividual \underline{C}ausal \underline{E}ffects (SCIENCE), a framework designed to construct more efficient prediction intervals for ITEs. SCIENCE accommodates the covariate shifts between source data and target data and applies to various data configurations, including semi-supervised and surrogate-assisted semi-supervised learning. Leveraging semi-parametric efficiency theory, SCIENCE produces rate double-robust prediction intervals under mild rate convergence conditions, permitting the use of flexible non-parametric models to estimate nuisance functions. We quantify efficiency gains by comparing semi-parametric efficiency bounds with and without the surrogates. Simulation studies demonstrate that our surrogate-assisted intervals offer substantial efficiency improvements over existing methods while maintaining valid group-conditional coverage. Applied to the phase 3 Moderna COVE COVID-19 vaccine trial, SCIENCE illustrates how multiple surrogate markers can be leveraged to generate more efficient prediction intervals.
Tobacco3482 is a widely used document classification benchmark dataset. However, our manual inspection of the entire dataset uncovers widespread ontological issues, especially large amounts of annotation label problems in the dataset. We establish data label guidelines and find that 11.7% of the dataset is improperly annotated and should either have an unknown label or a corrected label, and 16.7% of samples in the dataset have multiple valid labels. We then analyze the mistakes of a top-performing model and find that 35% of the model's mistakes can be directly attributed to these label issues, highlighting the inherent problems with using a noisily labeled dataset as a benchmark. Supplementary material, including dataset annotations and code, is available at https://github.com/gordon-lim/tobacco3482-mistakes/.
In radar-camera 3D object detection, the radar point clouds are sparse and noisy, which causes difficulties in fusing camera and radar modalities. To solve this, we introduce a novel query-based detection method named Radar-Camera Transformer (RCTrans). Specifically, we first design a Radar Dense Encoder to enrich the sparse valid radar tokens, and then concatenate them with the image tokens. By doing this, we can fully explore the 3D information of each interest region and reduce the interference of empty tokens during the fusing stage. We then design a Pruning Sequential Decoder to predict 3D boxes based on the obtained tokens and random initialized queries. To alleviate the effect of elevation ambiguity in radar point clouds, we gradually locate the position of the object via a sequential fusion structure. It helps to get more precise and flexible correspondences between tokens and queries. A pruning training strategy is adopted in the decoder, which can save much time during inference and inhibit queries from losing their distinctiveness. Extensive experiments on the large-scale nuScenes dataset prove the superiority of our method, and we also achieve new state-of-the-art radar-camera 3D detection results. Our implementation is available at https://github.com/liyih/RCTrans.
Constructing confidence intervals (CIs) for the average treatment effect (ATE) from patient records is crucial to assess the effectiveness and safety of drugs. However, patient records typically come from different hospitals, thus raising the question of how multiple observational datasets can be effectively combined for this purpose. In our paper, we propose a new method that estimates the ATE from multiple observational datasets and provides valid CIs. Our method makes little assumptions about the observational datasets and is thus widely applicable in medical practice. The key idea of our method is that we leverage prediction-powered inferences and thereby essentially `shrink' the CIs so that we offer more precise uncertainty quantification as compared to na\"ive approaches. We further prove the unbiasedness of our method and the validity of our CIs. We confirm our theoretical results through various numerical experiments. Finally, we provide an extension of our method for constructing CIs from combinations of experimental and observational datasets.
Answer Set Programming (ASP), a well-known declarative logic programming paradigm, has recently found practical application in Process Mining. In particular, ASP has been used to model tasks involving declarative specifications of business processes. In this area, Declare stands out as the most widely adopted declarative process modeling language, offering a means to model processes through sets of constraints valid traces must satisfy, that can be expressed in Linear Temporal Logic over Finite Traces (LTLf). Existing ASP-based solutions encode Declare constraints by modeling the corresponding LTLf formula or its equivalent automaton which can be obtained using established techniques. In this paper, we introduce a novel encoding for Declare constraints that directly models their semantics as ASP rules, eliminating the need for intermediate representations. We assess the effectiveness of this novel approach on two Process Mining tasks by comparing it with alternative ASP encodings and a Python library for Declare. Under consideration in Theory and Practice of Logic Programming (TPLP).
Inverse protein folding generates valid amino acid sequences that can fold into a desired protein structure, with recent deep-learning advances showing significant potential and competitive performance. However, challenges remain in predicting highly uncertain regions, such as those with loops and disorders. To tackle such low-confidence residue prediction, we propose a \textbf{Ma}sk \textbf{p}rior-guided denoising \textbf{Diff}usion (\textbf{MapDiff}) framework that accurately captures both structural and residue interactions for inverse protein folding. MapDiff is a discrete diffusion probabilistic model that iteratively generates amino acid sequences with reduced noise, conditioned on a given protein backbone. To incorporate structural and residue interactions, we develop a graph-based denoising network with a mask prior pre-training strategy. Moreover, in the generative process, we combine the denoising diffusion implicit model with Monte-Carlo dropout to improve uncertainty estimation. Evaluation on four challenging sequence design benchmarks shows that MapDiff significantly outperforms state-of-the-art methods. Furthermore, the in-silico sequences generated by MapDiff closely resemble the physico-chemical and structural characteristics of native proteins across different protein families and architectures.
We develop a probabilistic variant of Partial Least Squares (PLS) we call Probabilistic Targeted Factor Analysis (PTFA), which can be used to extract common factors in predictors that are useful to predict a set of predetermined target variables. Along with the technique, we provide an efficient expectation-maximization (EM) algorithm to learn the parameters and forecast the targets of interest. We develop a number of extensions to missing-at-random data, stochastic volatility, factor dynamics, and mixed-frequency data for real-time forecasting. In a simulation exercise, we show that PTFA outperforms PLS at recovering the common underlying factors affecting both features and target variables delivering better in-sample fit, and providing valid forecasts under contamination such as measurement error or outliers. Finally, we provide three applications in Economics and Finance where PTFA outperforms compared with PLS and Principal Component Analysis (PCA) at out-of-sample forecasting.
This paper introduces M$^{3}$-20M, a large-scale Multi-Modal Molecule dataset that contains over 20 million molecules, with the data mainly being integrated from existing databases and partially generated by large language models. Designed to support AI-driven drug design and discovery, M$^{3}$-20M is 71 times more in the number of molecules than the largest existing dataset, providing an unprecedented scale that can highly benefit the training or fine-tuning of models, including large language models for drug design and discovery tasks. This dataset integrates one-dimensional SMILES, two-dimensional molecular graphs, three-dimensional molecular structures, physicochemical properties, and textual descriptions collected through web crawling and generated using GPT-3.5, offering a comprehensive view of each molecule. To demonstrate the power of M$^{3}$-20M in drug design and discovery, we conduct extensive experiments on two key tasks: molecule generation and molecular property prediction, using large language models including GLM4, GPT-3.5, GPT-4, and Llama3-8b. Our experimental results show that M$^{3}$-20M can significantly boost model performance in both tasks. Specifically, it enables the models to generate more diverse and valid molecular structures and achieve higher property prediction accuracy than existing single-modal datasets, which validates the value and potential of M$^{3}$-20M in supporting AI-driven drug design and discovery. The dataset is available at https://github.com/bz99bz/M-3.
Hyperspectral and Multispectral Image Fusion (HMIF) aims to fuse low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs) to reconstruct high spatial and high spectral resolution images. Current methods typically apply direct fusion from the two modalities without effective supervision, leading to an incomplete perception of deep modality-complementary information and a limited understanding of inter-modality correlations. To address these issues, we propose a simple yet effective solution for unsupervised HMIF, revealing that modality decoupling is key to improving fusion performance. Specifically, we propose an end-to-end self-supervised \textbf{Mo}dality-Decoupled \textbf{S}patial-\textbf{S}pectral Fusion (\textbf{MossFuse}) framework that decouples shared and complementary information across modalities and aggregates a concise representation of both LR-HSIs and HR-MSIs to reduce modality redundancy. Also, we introduce the subspace clustering loss as a clear guide to decouple modality-shared features from modality-complementary ones. Systematic experiments over multiple datasets demonstrate that our simple and effective approach consistently outperforms the existing HMIF methods while requiring considerably fewer parameters with reduced inference time. The anonymous source code is in \href{https://github.com/dusongcheng/MossFuse}{MossFuse}.
Prefix circuits are fundamental components in digital adders, widely used in digital systems due to their efficiency in calculating carry signals. Synthesizing prefix circuits with minimized area and delay is crucial for enhancing the performance of modern computing systems. Recently, large language models (LLMs) have demonstrated a surprising ability to perform text generation tasks. We propose PrefixLLM, that leverages LLMs for prefix circuit synthesis. PrefixLLM transforms the prefix circuit synthesis task into a structured text generation problem, termed the Structured Prefix Circuit Representation (SPCR), and introduces an iterative framework to automatically and accurately generate valid SPCRs. We further present a design space exploration (DSE) framework that uses LLMs to iteratively search for area and delay optimized prefix circuits. Compared to state-of-the-art, PrefixLLM can reduce the area by 3.70% under the same delay constraint. This work highlights the use of LLMs in the synthesis of arithmetic circuits, which can be transformed into the structured text generation.
Constructing valid confidence sets is a crucial task in statistical inference, yet traditional methods often face challenges when dealing with complex models or limited observed sample sizes. These challenges are frequently encountered in modern applications, such as Likelihood-Free Inference (LFI). In these settings, confidence sets may fail to maintain a confidence level close to the nominal value. In this paper, we introduce two novel methods, TRUST and TRUST++, for calibrating confidence sets to achieve distribution-free conditional coverage. These methods rely entirely on simulated data from the statistical model to perform calibration. Leveraging insights from conformal prediction techniques adapted to the statistical inference context, our methods ensure both finite-sample local coverage and asymptotic conditional coverage as the number of simulations increases, even if n is small. They effectively handle nuisance parameters and provide computationally efficient uncertainty quantification for the estimated confidence sets. This allows users to assess whether additional simulations are necessary for robust inference. Through theoretical analysis and experiments on models with both tractable and intractable likelihoods, we demonstrate that our methods outperform existing approaches, particularly in small-sample regimes. This work bridges the gap between conformal prediction and statistical inference, offering practical tools for constructing valid confidence sets in complex models.
Systems that answer questions by reviewing the scientific literature are becoming increasingly feasible. To draw reliable conclusions, these systems should take into account the quality of available evidence, placing more weight on studies that use a valid methodology. We present a benchmark for measuring the methodological strength of biomedical papers, drawing on the risk-of-bias framework used for systematic reviews. The four benchmark tasks, drawn from more than 500 papers, cover the analysis of research study methodology, followed by evaluation of risk of bias in these studies. The benchmark contains 2000 expert-generated bias annotations, and a human-validated pipeline for fine-grained alignment with research paper content. We evaluate a range of large language models on the benchmark, and find that these models fall significantly short of expert-level performance. By providing a standardized tool for measuring judgments of study quality, the benchmark can help to guide systems that perform large-scale aggregation of scientific data. The dataset is available at https://github.com/RoBBR-Benchmark/RoBBR.
Model selection/optimization in conformal inference is challenging, since it may break the exchangeability between labeled and unlabeled data. We study this problem in the context of conformal selection, which uses conformal p-values to select ``interesting'' instances with large unobserved labels from a pool of unlabeled data, while controlling the FDR in finite sample. For validity, existing solutions require the model choice to be independent of the data used to construct the p-values and calibrate the selection set. However, when presented with many model choices and limited labeled data, it is desirable to (i) select the best model in a data-driven manner, and (ii) mitigate power loss due to sample splitting. This paper presents OptCS, a general framework that allows valid statistical testing (selection) after flexible data-driven model optimization. We introduce general conditions under which OptCS constructs valid conformal p-values despite substantial data reuse and handles complex p-value dependencies to maintain finite-sample FDR control via a novel multiple testing procedure. We instantiate this general recipe to propose three FDR-controlling procedures, each optimizing the models differently: (i) selecting the most powerful one among multiple pre-trained candidate models, (ii) using all data for model fitting without sample splitting, and (iii) combining full-sample model fitting and selection. We demonstrate the efficacy of our methods via simulation studies and real applications in drug discovery and alignment of large language models in radiology report generation.
Large Vision-Language Models (LVLMs) have demonstrated outstanding performance in multimodal task reasoning. However, they often generate responses that appear plausible yet do not accurately reflect the visual content, a phenomenon known as hallucination. Recent approaches have introduced training-free methods that mitigate hallucinations by adjusting the decoding strategy during inference stage, typically attributing hallucination to the language model itself. Our analysis, however, reveals that distortions in the visual encoding process significantly affect the model's reasoning accuracy. Specifically, earlier visual layers may retain key features but gradually distort as the information propagates toward the output layer. Building on these findings, we propose a novel hallucination-mitigation method from the visual encoding perspective: \textbf{V}isu\textbf{a}l \textbf{L}ayer Fus\textbf{i}on Contrastive \textbf{D}ecoding (VaLiD). This method utilizes uncertainty to guide the selection of visual hidden layers, correcting distortions in the visual encoding process and thereby improving the reliability of generated text. Experimental results show that VaLiD effectively reduces hallucinations across various benchmarks, achieving state-of-the-art performance compared to multiple baseline methods.
Existing methods to summarize posterior inference for mixture models focus on identifying a point estimate of the implied random partition for clustering, with density estimation as a secondary goal (Wade and Ghahramani, 2018; Dahl et al., 2022). We propose a novel approach for summarizing posterior inference in nonparametric Bayesian mixture models, prioritizing estimation of the mixing measure (or mixture) as an inference target. One of the key features is the model-agnostic nature of the approach, which remains valid under arbitrarily complex dependence structures in the underlying sampling model. Using a decision-theoretic framework, our method identifies a point estimate by minimizing posterior expected loss. A loss function is defined as a discrepancy between mixing measures. Estimating the mixing measure implies inference on the mixture density and the random partition. Exploiting the discrete nature of the mixing measure, we use a version of sliced Wasserstein distance. We introduce two specific variants for Gaussian mixtures. The first, mixed sliced Wasserstein, applies generalized geodesic projections on the product of the Euclidean space and the manifold of symmetric positive definite matrices. The second, sliced mixture Wasserstein, leverages the linearity of Gaussian mixture measures for efficient projection
Estimating three-dimensional conformations of a molecular graph allows insight into the molecule's biological and chemical functions. Fast generation of valid conformations is thus central to molecular modeling. Recent advances in graph-based deep networks have accelerated conformation generation from hours to seconds. However, current network architectures do not scale well to large molecules. Here we present ConfFlow, a flow-based model for conformation generation based on transformer networks. In contrast with existing approaches, ConfFlow directly samples in the coordinate space without enforcing any explicit physical constraints. The generative procedure is highly interpretable and is akin to force field updates in molecular dynamics simulation. When applied to the generation of large molecule conformations, ConfFlow improve accuracy by up to $40\%$ relative to state-of-the-art learning-based methods. The source code is made available at https://github.com/IntelLabs/ConfFlow.
Integrating robotically driven contact-based material characterization techniques into self-driving laboratories can enhance measurement quality, reliability, and throughput. While deep learning models support robust autonomy, current methods lack reliable pixel-precision positioning and require extensive labeled data. To overcome these challenges, we propose an approach for building self-supervised autonomy into contact-based robotic systems that teach the robot to follow domain expert measurement principles at high-throughputs. Firstly, we design a vision-based, self-supervised convolutional neural network (CNN) architecture that uses differentiable image priors to optimize domain-specific objectives, refining the pixel precision of predicted robot contact poses by 20.0% relative to existing approaches. Secondly, we design a reliable graph-based planner for generating distance-minimizing paths to accelerate the robot measurement throughput and decrease planning variance by 6x. We demonstrate the performance of this approach by autonomously driving a 4-degree-of-freedom robotic probe for 24 hours to characterize semiconductor photoconductivity at 3,025 uniquely predicted poses across a gradient of drop-casted perovskite film compositions, achieving throughputs over 125 measurements per hour. Spatially mapping photoconductivity onto each drop-casted film reveals compositional trends and regions of inhomogeneity, valuable for identifying manufacturing process defects. With this self-supervised CNN-driven robotic system, we enable high-precision and reliable automation of contact-based characterization techniques at high throughputs, thereby allowing the measurement of previously inaccessible yet important semiconductor properties for self-driving laboratories.