PyTorchKR Papers

최신 논문

총 2,107편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2405.01708v2cs.LG

A deep causal inference model for interpretable travel behaviour analysis

Transportation policy assessment often involves causal questions, yet traditional travel behaviour lacks the ability of distinguishing causal association from non-causal correlations. We present the deep CAusal infeRence mOdel for traveL behavIour aNAlysis (CAROLINA), a novel framework that addresses both observed and unobserved confounders in discrete choice modelling through causal discovery and the strengths of deep neural networks. Within this interpretable framework, we also introduce a Generative Counterfactual model for forecasting individuals' behaviour by adapting the Normalizing Flow method. Through the case studies of virtual reality-based pedestrian crossing behaviour, revealed preference travel behaviour from London, and synthetic data, we demonstrate the effectiveness of our proposed models in isolating causal relationships from confounding associations. Our proposed causal framework enhances predictive accuracy by employing data-driven algorithms, while maintaining interpretability. In addition, the counterfactual results show that intervention mechanisms that can reduce pedestrian stress levels lead to a 35.35% increase in individuals experiencing shorter waiting times. External interventions that reduce travel distances of non-mandatory trips in London lead to a 47% increase in the possible use of active and public transit modes.

arXiv:2610.00012v2cs.AI

인과적 세계 모델은 모듈형 LLM 에이전트에 언제 도움이 되는가

When Do Causal World Models Help Modular LLM Agents

LLM agents increasingly operate in modular systems, where planning requires coordinating multiple functional components whose actions can causally change downstream states and behaviors. This makes intervention-aware prediction essential: an agent must anticipate not only what is likely to happen next, but what will happen as a consequence of its own actions. We find that purely observational world models can incur irreducible intervention-time error in such systems, even when they accurately model observational trajectories. To address this limitation, we propose CausalCompose, a causal world-model framework that equips modular LLM agents with causal structure for intervention-aware prediction and planning. We theoretically show that causal composition can overcome this intervention gap with sufficient evidence and controlled local error. Experiments across diverse modular agent environments validate these results: incorporating causal structure consistently improves intervention-sensitive reasoning and planning, with particularly clear gains in structured tool-use systems where causal dependencies directly govern action execution. Our results show when causal world models help modular LLM agents: when causal dependencies are identifiable and actionable for planning.

arXiv:2609.38810v3cs.CV

CRAFT: 의료 비전-언어 모델의 인과적 책임 및 실패 추적

CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models

As vision language models are increasingly deployed in clinical diagnosis, understanding how they internally resolve competing visual and textual signals becomes a safety imperative. Existing mechanistic analyses remain confined to unimodal text and offer no explanation for why a single misleading sentence can override a correct image based diagnosis, or why a model commits to a confident answer despite insufficient visual evidence. We find that these two safety risks, arbitration failure where textual context overrides visual grounding and brake failure where the model commits without adequate evidence, are mediated by spatially disjoint attention head populations: arbitration heads form a mid-to-deep wideband reflecting cross-layer evidence competition, while brake heads concentrate in a narrow middle-to-late layer band that regulates evidence sufficiency and abstention behavior. To ground these observations in causal circuitry, we introduce CRAFT, which localizes each failure mode to a minimal causal head set via dual criteria and verifies necessity and sufficiency through temporal probes and Tuned Lens trajectory analysis. Excising arbitration heads sharply reduces conflict following with negligible degradation on clean inputs, while excising brake heads restores appropriate abstention under degraded visual evidence. The two interventions target spatially disjoint head sets and produce distinct corrective effects, underscoring the mechanistic separability of the failure modes. Experiments across multiple medical VQA benchmarks and VLM architectures validate both the localization and interventions, demonstrating that the identified heads causally drive each failure mode and that targeted modulation generalises without retraining. The code is available at https://github.com/zhcz328/CRAFT.

arXiv:2609.26707v2stat.ME

Optimal Expert Annotation for Evaluating Sequential Decision Policies from Text Records

Offline reinforcement learning and off-policy evaluation evaluate dynamic decision rules based on historical data, without the ability to deploy online. In recent artificial intelligence (AI) applications, simple state and reward information is recorded as complex text or image, expert annotation may be available but at a higher cost. Recent AI and machine learning (ML) predictors can label data cheaply but with unknown bias. We show how a limited budget for ground-truth data-annotation can safely make use of plentiful ML predictions in a new estimator for doubly-robust off-policy evaluation with missing rewards. Our method directs where data should be collected by optimizing annotation probabilities for the best downstream estimation variance, which we implement in a feasible batch-adaptive approach. Our work is motivated by a collaboration with a homelessness services nonprofit that writes casenotes for individuals over time. Our method can be used to unlock trustworthy inference from casenote data and answer new inferential questions such as: how does expanding outreach effort over time affect progress towards a housing application and improvement in housing placement? In simulations and on two real datasets -- casenotes from the nonprofit and human-preference votes from LMArena -- we see reductions in RMSE of 37-65% for housing placement and 21-67% for progress towards a housing application at budgets of 50% of full annotation and above, and by 55-62% at every budget on LMArena under an equal-exposure policy.

arXiv:2606.24832v2cs.AI

Difference-Making without Making a Difference

Over a series of seven papers, Andreas & G\"unther have introduced seven definitions of actual causation and have classified them as belonging to three different, competing, types of accounts: factual difference-making, counterfactual difference-making, and regularity-based. I show that their most recent -- factual difference-making -- definition instantiates all three types, thereby proving that these are distinctions without a difference. I further compare their novel account to the other six accounts on several crucial examples, revealing that this undermines all seven of their accounts.

arXiv:2601.16407v5cs.CL

Jacobian Scopes: A Unified Geometric Framework for Token-Level LLM Attribution

Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prior tokens most strongly influence a given prediction remains challenging due to the proliferation of layers and attention heads in modern architectures. We propose Jacobian Scopes, a suite of gradient-based, token level causal attribution methods for interpreting LLM predictions. Grounded in perturbation theory and information geometry, Jacobian Scopes quantify how input tokens influence various aspects of a model's prediction, such as specific logits, the full predictive distribution, and model uncertainty (effective temperature). Through case studies spanning instruction understanding, translation, and in-context learning (ICL), we demonstrate how Jacobian Scopes reveal implicit political biases, uncover word- and phrase-level translation strategies, and shed light on recently debated mechanisms underlying in-context time-series forecasting. On token-ablation faithfulness benchmarks (LAMBADA and IWSLT2017) across six LLMs, the distribution-level Fisher and Temperature Scopes significantly outperform established gradient-based attribution methods in 10 of 12 model-dataset settings. To facilitate exploration of Jacobian Scopes on custom text, we open-source our implementations and provide a cloud-hosted interactive demo at https://huggingface.co/spaces/Typony/JacobianScopes.

arXiv:2410.14789v3stat.ME

Differentially Private Covariate Balancing Causal Inference

Differential privacy is the leading mathematical framework for privacy protection, providing a probabilistic guarantee that safeguards individuals' private information when publishing statistics from a dataset. This guarantee is achieved by applying a randomized algorithm to the original data, which introduces unique challenges in data analysis by distorting inherent patterns. In particular, causal inference using observational data while preserving privacy is challenging because it requires a good covariate balance between treatment groups, but checking the covariate balance is challenging when privacy is a primary concern because releasing any statistic (e.g., t-statistic) for the balance check compromises privacy. Additionally, the performance of the privatized estimator critically depends on the choice of differential privacy mechanisms, and it remains unexplored how privacy-protecting causal inference could be conducted with observational data. In this article, we present a differentially private two-stage covariate balancing weighting estimator to infer causal effects from observational data. Our algorithm produces both point and interval estimators with statistical guarantees, such as covariate balance, rate optimality, and oracle budget allocation, under a given privacy budget.

arXiv:2507.05526

Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning

In scientific domains -- from biology to the social sciences -- many questions boil down to \textit{What effect will we observe if we intervene on a particular variable?} If the causal relationships (e.g.~a causal graph) are known, it is possible to estimate the intervention distributions. In the absence of this domain knowledge, the causal structure must be discovered from the available observational data. However, observational data are often compatible with multiple causal graphs, making methods that commit to a single structure prone to overconfidence. A principled way to manage this structural uncertainty is via Bayesian inference, which averages over a posterior distribution on possible causal structures and functional mechanisms. Unfortunately, the number of causal structures grows super-exponentially with the number of nodes in the graph, making computations intractable. We propose to circumvent these challenges by using meta-learning to create an end-to-end model: the Model-Averaged Causal Estimation Transformer Neural Process (MACE-TNP). The model is trained to predict the Bayesian model-averaged interventional posterior distribution, and its end-to-end nature bypasses the need for expensive calculations. Empirically, we demonstrate that MACE-TNP outperforms strong Bayesian baselines. Our work establishes meta-learning as a flexible and scalable paradigm for approximating complex Bayesian causal inference, that can be scaled to increasingly challenging settings in the future.

arXiv:2506.18147

Causal Interventions in Bond Multi-Dealer-to-Client Platforms

The digitalization of financial markets has shifted trading from voice to electronic channels, with Multi-Dealer-to-Client (MD2C) platforms now enabling clients to request quotes (RfQs) for financial instruments like bonds from multiple dealers simultaneously. In this competitive landscape, dealers cannot see each other's prices, making a rigorous analysis of the negotiation process crucial to ensure their profitability. This article introduces a novel general framework for analyzing the RfQ process using probabilistic graphical models and causal inference. Within this framework, we explore different inferential questions that are relevant for dealers participating in MD2C platforms, such as the computation of optimal prices, estimating potential revenues and the identification of clients that might be interested in trading the dealer's axes. We then move into analyzing two different approaches for model specification: a generative model built on the work of (Fermanian, Gu\'eant & Pu, 2017); and discriminative models utilizing machine learning techniques. We evaluate these methodologies using predictive metrics designed to assess their effectiveness in the context of optimal pricing, highlighting the relative benefits of using models that take into account the internal mechanisms of the negotiation process.

arXiv:2506.14950

Double Machine Learning for Conditional Moment Restrictions: IV Regression, Proximal Causal Learning and Beyond

Solving conditional moment restrictions (CMRs) is a key problem considered in statistics, causal inference, and econometrics, where the aim is to solve for a function of interest that satisfies some conditional moment equalities. Specifically, many techniques for causal inference, such as instrumental variable (IV) regression and proximal causal learning (PCL), are CMR problems. Most CMR estimators use a two-stage approach, where the first-stage estimation is directly plugged into the second stage to estimate the function of interest. However, naively plugging in the first-stage estimator can cause heavy bias in the second stage. This is particularly the case for recently proposed CMR estimators that use deep neural network (DNN) estimators for both stages, where regularisation and overfitting bias is present. We propose DML-CMR, a two-stage CMR estimator that provides an unbiased estimate with fast convergence rate guarantees. We derive a novel learning objective to reduce bias and develop the DML-CMR algorithm following the double/debiased machine learning (DML) framework. We show that our DML-CMR estimator can achieve the minimax optimal convergence rate of $O(N^{-1/2})$ under parameterisation and mild regularity conditions, where $N$ is the sample size. We apply DML-CMR to a range of problems using DNN estimators, including IV regression and proximal causal learning on real-world datasets, demonstrating state-of-the-art performance against existing CMR estimators and algorithms tailored to those problems.

arXiv:2506.16629공식 코드 · Papers with Code

Learning Causally Predictable Outcomes from Psychiatric Longitudinal Data

Causal inference in longitudinal biomedical data remains a central challenge, especially in psychiatry, where symptom heterogeneity and latent confounding frequently undermine classical estimators. Most existing methods for treatment effect estimation presuppose a fixed outcome variable and address confounding through observed covariate adjustment. However, the assumption of unconfoundedness may not hold for a fixed outcome in practice. To address this foundational limitation, we directly optimize the outcome definition to maximize causal identifiability. Our DEBIAS (Durable Effects with Backdoor-Invariant Aggregated Symptoms) algorithm learns non-negative, clinically interpretable weights for outcome aggregation, maximizing durable treatment effects and empirically minimizing both observed and latent confounding by leveraging the time-limited direct effects of prior treatments in psychiatric longitudinal data. The algorithm also furnishes an empirically verifiable test for outcome unconfoundedness. DEBIAS consistently outperforms state-of-the-art methods in recovering causal effects for clinically interpretable composite outcomes across comprehensive experiments in depression and schizophrenia.

arXiv:2506.12218

Directed Acyclic Graph Convolutional Networks

Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and neural architecture search. In this work, we introduce the DAG Convolutional Network (DCN), a novel graph neural network (GNN) architecture designed specifically for convolutional learning from signals supported on DAGs. The DCN leverages causal graph filters to learn nodal representations that account for the partial ordering inherent to DAGs, a strong inductive bias does not present in conventional GNNs. Unlike prior art in machine learning over DAGs, DCN builds on formal convolutional operations that admit spectral-domain representations. We further propose the Parallel DCN (PDCN), a model that feeds input DAG signals to a parallel bank of causal graph-shift operators and processes these DAG-aware features using a shared multilayer perceptron. This way, PDCN decouples model complexity from graph size while maintaining satisfactory predictive performance. The architectures' permutation equivariance and expressive power properties are also established. Comprehensive numerical tests across several tasks, datasets, and experimental conditions demonstrate that (P)DCN compares favorably with state-of-the-art baselines in terms of accuracy, robustness, and computational efficiency. These results position (P)DCN as a viable framework for deep learning from DAG-structured data that is designed from first (graph) signal processing principles.

arXiv:2506.18929

International Trade and Intellectual Property

Intellectual property (IP) rules have the potential to shape cross-border trade far more than their legalistic origins might suggest. Drawing on three decades of evidence, this review shows that stronger IP rights simultaneously create market-power forces that raise prices and market-expansion forces that broaden demand, while dynamic incentives spur quality upgrading and new export varieties. Micro-data and quasi-natural experiments after TRIPS reveal that IP most often boosts trade along the extensive margin and redirects some activity toward licensing and foreign investment. Policy bundling and measurement gaps on the strength of IP rights still cloud causal inference. Future work must map intangible flows and enforcement quality to capture the digital, data-driven frontier of international commerce.

arXiv:2506.18001

An Empirical Comparison of Weak-IV-Robust Procedures in Just-Identified Models

Instrumental variable (IV) regression is recognized as one of the five core methods for causal inference, as identified by Angrist and Pischke (2008). This paper compares two leading approaches to inference under weak identification for just-identified IV models: the classical Anderson-Rubin (AR) procedure and the recently popular tF method proposed by Lee et al. (2022). Using replication data from the American Economic Review (AER) and Monte Carlo simulation experiments, we evaluate the two procedures in terms of statistical significance testing and confidence interval (CI) length. Empirically, we find that the AR procedure typically offers higher power and yields shorter CIs than the tF method. Nonetheless, as noted by Lee et al. (2022), tF has a theoretical advantage in terms of expected CI length. Our findings suggest that the two procedures may be viewed as complementary tools in empirical applications involving potentially weak instruments.

arXiv:2506.12765

Rethinking Distributional IVs: KAN-Powered D-IV-LATE & Model Choice

The double/debiased machine learning (DML) framework has become a cornerstone of modern causal inference, allowing researchers to utilise flexible machine learning models for the estimation of nuisance functions without introducing first-order bias into the final parameter estimate. However, the choice of machine learning model for the nuisance functions is often treated as a minor implementation detail. In this paper, we argue that this choice can have a profound impact on the substantive conclusions of the analysis. We demonstrate this by presenting and comparing two distinct Distributional Instrumental Variable Local Average Treatment Effect (D-IV-LATE) estimators. The first estimator leverages standard machine learning models like Random Forests for nuisance function estimation, while the second is a novel estimator employing Kolmogorov-Arnold Networks (KANs). We establish the asymptotic properties of these estimators and evaluate their performance through Monte Carlo simulations. An empirical application analysing the distributional effects of 401(k) participation on net financial assets reveals that the choice of machine learning model for nuisance functions can significantly alter substantive conclusions, with the KAN-based estimator suggesting more complex treatment effect heterogeneity. These findings underscore a critical "caveat emptor". The selection of nuisance function estimators is not a mere implementation detail. Instead, it is a pivotal choice that can profoundly impact research outcomes in causal inference.

arXiv:2506.14805

Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?

As Multimodal Large Language Models (MLLMs) continue to evolve, their cognitive and reasoning capabilities have seen remarkable progress. However, challenges in visual fine-grained perception and commonsense causal inference persist. This paper introduces Argus Inspection, a multimodal benchmark with two levels of difficulty, emphasizing detailed visual recognition while incorporating real-world commonsense understanding to evaluate causal reasoning abilities. Expanding on it, we present the Eye of Panoptes framework, which integrates a binary parametric Sigmoid metric with an indicator function, enabling a more holistic evaluation of MLLMs' responses in opinion-based reasoning tasks. Experiments conducted on 26 mainstream MLLMs reveal that the highest performance in visual fine-grained reasoning reaches only 0.46, highlighting considerable potential for enhancement. Our research offers valuable perspectives for the continued refinement of MLLMs.

arXiv:2506.18559

T-CPDL: A Temporal Causal Probabilistic Description Logic for Developing Logic-RAG Agent

Large language models excel at generating fluent text but frequently struggle with structured reasoning involving temporal constraints, causal relationships, and probabilistic reasoning. To address these limitations, we propose Temporal Causal Probabilistic Description Logic (T-CPDL), an integrated framework that extends traditional Description Logic with temporal interval operators, explicit causal relationships, and probabilistic annotations. We present two distinct variants of T-CPDL: one capturing qualitative temporal relationships through Allen's interval algebra, and another variant enriched with explicit timestamped causal assertions. Both variants share a unified logical structure, enabling complex reasoning tasks ranging from simple temporal ordering to nuanced probabilistic causation. Empirical evaluations on temporal reasoning and causal inference benchmarks confirm that T-CPDL substantially improves inference accuracy, interpretability, and confidence calibration of language model outputs. By delivering transparent reasoning paths and fine-grained temporal and causal semantics, T-CPDL significantly enhances the capability of language models to support robust, explainable, and trustworthy decision-making. This work also lays the groundwork for developing advanced Logic-Retrieval-Augmented Generation (Logic-RAG) frameworks, potentially boosting the reasoning capabilities and efficiency of knowledge graph-enhanced RAG systems.

arXiv:2506.19191

Bayesian Evolutionary Swarm Architecture: A Formal Epistemic System Grounded in Truth-Based Competition

We introduce a mathematically rigorous framework for an artificial intelligence system composed of probabilistic agents evolving through structured competition and belief revision. The architecture, grounded in Bayesian inference, measure theory, and population dynamics, defines agent fitness as a function of alignment with a fixed external oracle representing ground truth. Agents compete in a discrete-time environment, adjusting posterior beliefs through observed outcomes, with higher-rated agents reproducing and lower-rated agents undergoing extinction. Ratings are updated via pairwise truth-aligned utility comparisons, and belief updates preserve measurable consistency and stochastic convergence. We introduce hash-based cryptographic identity commitments to ensure traceability, alongside causal inference operators using do-calculus. Formal theorems on convergence, robustness, and evolutionary stability are provided. The system establishes truth as an evolutionary attractor, demonstrating that verifiable knowledge arises from adversarial epistemic pressure within a computable, self-regulating swarm.

arXiv:2506.15758

Linear-Time Primitives for Algorithm Development in Graphical Causal Inference

We introduce CIfly, a framework for efficient algorithmic primitives in graphical causal inference that isolates reachability as a reusable core operation. It builds on the insight that many causal reasoning tasks can be reduced to reachability in purpose-built state-space graphs that can be constructed on the fly during traversal. We formalize a rule table schema for specifying such algorithms and prove they run in linear time. We establish CIfly as a more efficient alternative to the common primitives moralization and latent projection, which we show are computationally equivalent to Boolean matrix multiplication. Our open-source Rust implementation parses rule table text files and runs the specified CIfly algorithms providing high-performance execution accessible from Python and R. We demonstrate CIfly's utility by re-implementing a range of established causal inference tasks within the framework and by developing new algorithms for instrumental variables. These contributions position CIfly as a flexible and scalable backbone for graphical causal inference, guiding algorithm development and enabling easy and efficient deployment.

arXiv:2506.16697

From Prompts to Constructs: A Dual-Validity Framework for LLM Research in Psychology

Large language models (LLMs) are rapidly being adopted across psychology, serving as research tools, experimental subjects, human simulators, and computational models of cognition. However, the application of human measurement tools to these systems can produce contradictory results, raising concerns that many findings are measurement phantoms--statistical artifacts rather than genuine psychological phenomena. In this Perspective, we argue that building a robust science of AI psychology requires integrating two of our field's foundational pillars: the principles of reliable measurement and the standards for sound causal inference. We present a dual-validity framework to guide this integration, which clarifies how the evidence needed to support a claim scales with its scientific ambition. Using an LLM to classify text may require only basic accuracy checks, whereas claiming it can simulate anxiety demands a far more rigorous validation process. Current practice systematically fails to meet these requirements, often treating statistical pattern matching as evidence of psychological phenomena. The same model output--endorsing "I am anxious"--requires different validation strategies depending on whether researchers claim to measure, characterize, simulate, or model psychological constructs. Moving forward requires developing computational analogues of psychological constructs and establishing clear, scalable standards of evidence rather than the uncritical application of human measurement tools.