100 articles tagged #machine-learning
arXiv:2406.13128v2 Announce Type: replace-cross Abstract: Due to the intricate structure of vascular trees, minor segmentation errors can significantly alter connectivity patterns and increase variability in extracted morphological properties. Global metrics such as the Dice coefficient, precision,
arXiv:2606.29221v2 Announce Type: replace Abstract: We address the problem of online multi-human multi-robot matching through the lens of a linear matching bandit framework, where a learner assigns robots with unknown features from a fixed pool to distinct sets of human agents over multiple rounds.
arXiv:2505.08784v3 Announce Type: replace-cross Abstract: As machine learning (ML) enters high-stakes domains, trustworthy uncertainty quantification (UQ) is essential for safety. In this paper we introduce PCS-UQ, a framework based on the Predictability, Computability, and Stability (PCS) principle
arXiv:2505.00473v2 Announce Type: replace Abstract: We explore the promising performance of a transformer model in predicting outputs of parametric dynamical systems with external time-varying input signals. The outputs of such systems vary not only with physical parameters but also with external ti
arXiv:2607.20768v1 Announce Type: cross Abstract: Majority voting over LLMs is widely assumed to benefit from diversity, and diversity measures are used to choose which models to combine. We ask whether five such measures track diversity or mainly re-express capability, auditing them as predictors o
arXiv:2607.20656v1 Announce Type: cross Abstract: Effective decision-making in complex and changing environments requires balancing short-term and long-term consequences. In reinforcement learning (RL), this trade-off is typically controlled through a fixed discount factor, which imposes a single ex
arXiv:2607.20530v1 Announce Type: cross Abstract: Semi-supervised anomaly detection plays a key role in diverse fields such as process monitoring, healthcare, and finance. However, lightweight methods often struggle with high-dimensional data and typically require careful tuning of multiple hyperpar
arXiv:2607.06696v2 Announce Type: replace-cross Abstract: Weighted empirical measures on compact manifolds appear in importance sampling, particle approximations, posterior summaries, quadrature, and representation learning. Ordinary effective sample size and related weight summaries ignore the geom
arXiv:2512.04966v2 Announce Type: replace-cross Abstract: Accurate channel state information (CSI) underpins reliable and efficient wireless communication. However, acquiring CSI via pilot estimation incurs substantial overhead, especially in massive multiple-input multiple-output (MIMO) systems ope
arXiv:2604.14575v3 Announce Type: replace-cross Abstract: Marketing research often relies on parameters estimated from costly human-generated data, such as conjoint survey responses, purchase decisions, and field experiment outcomes. Recent advances in large language models (LLMs) and other AI syste
arXiv:2407.08233v3 Announce Type: replace Abstract: Current differentially private learning paradigms face a severe utility bottleneck: DP-SGD degrades performance through noise accumulation over training steps, while aggregation-based approaches such as PATE suffer from data inefficiency due to dis
arXiv:2604.08625v3 Announce Type: replace-cross Abstract: Benign overfitting describes the ability of minimum norm interpolating estimators to generalize despite fitting noisy data exactly. Existing characterizations depend on delicate spectral functionals of the population covariance operator, name
arXiv:2602.01051v5 Announce Type: replace Abstract: Repertoire-level analysis of T cell receptors offers a biologically grounded signal for disease detection and immune monitoring, yet practical deployment is impeded by label sparsity, cohort heterogeneity, and the computational burden of adapting l
arXiv:2602.03901v5 Announce Type: replace Abstract: The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization. We develop NeuroPareto, a cohesive architecture that integrat
arXiv:2607.19147v1 Announce Type: cross Abstract: Data-driven methods have revolutionized ocean modeling, yet current approaches rely heavily on complete reanalysis datasets, imposing computational constraints and limiting model performance to that of the training data. Here, we present a generative
arXiv:2607.09816v2 Announce Type: replace Abstract: Class imbalance poses a fundamental challenge in risk-sensitive applications such as fraud detection and medical diagnosis, where minority-class samples are scarce yet critical for accurate classification. Existing oversampling methods generate syn
arXiv:2607.18290v1 Announce Type: cross Abstract: In recent years, Kolmogorov-Arnold Networks (KANs) have attracted increasing attention due to their effectiveness in machine learning and scientific computing tasks, offering a new paradigm for neural network design. In this paper, we present SechKAN
arXiv:2607.18559v1 Announce Type: cross Abstract: Gaussian graphical model selection is usually studied under independent sampling, but in many applications the data arise as a single trajectory of a dependent stochastic process. We study exact recovery of the graph from one trajectory of random-sca
arXiv:2601.18930v4 Announce Type: replace-cross Abstract: We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as locking mechanisms. We cast this problem as learning the parameters of a discrete Partially Observable Markov Decision Process (POMD
arXiv:2607.18361v1 Announce Type: cross Abstract: Deep neural networks have become a promising approach for IMU-based sensing, but their scalability is fundamentally limited by costly labeled data and poor robustness to heterogeneous devices, placements, and users. Existing unsupervised and self-sup
arXiv:2411.10921v2 Announce Type: replace Abstract: Accurate forecasts of distributed solar generation are necessary to maintain grid stability amid the increased uptake of distributed solar photovoltaic (PV) systems. However, the high variability of solar generation over short time intervals (secon
arXiv:2607.17390v1 Announce Type: cross Abstract: Kernel regression with tensor trains and Hadamard overparameterization (KReTTaH) is introduced as a training-data-free, interpretable, and nonparametric framework for multi-way data imputation. The imputation problem is reformulated as regression in
arXiv:2607.17601v1 Announce Type: cross Abstract: Accurate protein-ligand binding affinity prediction is central to computational drug discovery, yet modern docking engines frequently disagree without indicating which prediction to trust. Consensus scoring and ensemble methods improve mean accuracy
arXiv:2607.03651v2 Announce Type: replace Abstract: While traditional hub capacity planning models optimize effectively for quantitative inputs, they often fail to digest qualitative business context. We propose a novel framework where a large language model (LLM) agent iteratively proposes hub capa
arXiv:2607.14733v1 Announce Type: new Abstract: Temporal Knowledge Graphs (TKGs) record how facts evolve over time, but forecasting future events on a TKG remains difficult for three reasons: (i) long-range temporal dependencies are hard to encode; (ii) events on different chains mutually excite or
arXiv:2607.14391v1 Announce Type: new Abstract: This study concentrates on predicting stock prices in the Egyptian market, focusing on the EGX30, an influential financial hub in the Middle East. While most research focuses on global stocks, there's a growing need to understand stock trends in develo
arXiv:2607.14318v1 Announce Type: new Abstract: We introduce COAT (Counterfactual Optimal Action Tree), a framework for learning interpretable prescriptive policies from observational data. COAT combines counterfactual outcome estimation with large-scale mixed-integer optimization, using column gene
arXiv:2607.14463v1 Announce Type: new Abstract: We study Dynamical System Autoencoders (DSAE) for LiDAR point-cloud classification using spatial coordinates and Product Coefficient feature augmentations. The experiments compare separately trained DSAE architectures at encoder depths $K=1,\ldots,5$ a
arXiv:2605.21751v2 Announce Type: replace Abstract: Text-to-optimization requires two separable capabilities: modeling -- choosing the right optimization structure -- and binding -- grounding every coefficient, index, and parameter in the concrete problem data. We study this via Text2Opt-Bench, a sc
arXiv:2607.14877v1 Announce Type: new Abstract: Reachability is the most fundamental logical objective, yet it is notoriously difficult to learn in reinforcement learning settings: even for Markov decision processes, PAC learning of reachability is impossible without additional assumptions. This dif
arXiv:2607.15018v1 Announce Type: cross Abstract: High-dimensional categorical data arise in genetics, biomedicine, and the social sciences, yet visualization tools for such data remain far less developed than those for continuous variables. Existing methods either scale poorly, rely heavily on low-
arXiv:2607.14398v1 Announce Type: cross Abstract: Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time op
arXiv:2607.14163v1 Announce Type: cross Abstract: Most single-cell foundation models are adapted from language models, representing each cell as a sequence of gene tokens. This discards the relationships among genes and often the magnitude of their expression. We present scVision, a vision foundatio
arXiv:2510.04876v3 Announce Type: replace-cross Abstract: Benthic habitat mapping is fundamental for understanding marine ecosystems, guiding conservation efforts, and supporting sustainable resource management. Yet, the scarcity of large, annotated datasets limits the development and benchmarking o
arXiv:2607.13479v1 Announce Type: cross Abstract: Estimating the full shape of a deformable object is especially challenging when vision is unavailable: in the dark, inside an opaque bag, behind the manipulating hand, or under heavy self-occlusion. Touch is the natural sensor in these settings, but
arXiv:2512.23043v3 Announce Type: replace Abstract: Federated Averaging (FedAvg) often degrades under non-IID client data, but it remains unclear whether this degradation reflects the loss of client-learned representations or a failure to use representations that are still present. We study this que
arXiv:2607.13847v1 Announce Type: cross Abstract: Many datasets encountered across a wide range of domains possess rich geometric and topological structure that is difficult to capture using conventional vector-based representations. Quantum machine learning offers the possibility of processing high
arXiv:2505.18231v3 Announce Type: replace-cross Abstract: Large Language Model (LLM) inference is typically memory-intensive, especially when processing large batch sizes and long sequences, due to the large size of key-value (KV) cache. Vector Quantization (VQ) is recently adopted to alleviate this
arXiv:2607.11970v1 Announce Type: cross Abstract: We develop an enhanced in-context learning (ICL) framework to improve the performance of pilot-based beamforming in multi-user multiple-input single-output (MU-MISO) systems. The proposed scheme integrates the ICL-Transformer backbone with the pilot
arXiv:2510.14907v2 Announce Type: replace-cross Abstract: We extend the study of learning in games to dynamics that exhibit non-asymptotic stability. We do so through the notion of uniform stability, which is concerned with equilibria of individually utility-seeking dynamics. Perhaps surprisingly, i
arXiv:2607.10926v1 Announce Type: new Abstract: Identifying heterogeneous treatment effects under unobserved confounding is central in observational causal inference. In proxy models with a discrete latent confounder, prior Synthetic Potential Outcomes (SPO) [Mazaheri-Squires-Uhler '25] recover the
arXiv:2607.10441v1 Announce Type: cross Abstract: Context engineering decides what information a model carries forward, and current designs meter it in tokens: compressing the past into a bounded recurrent state, keeping a key-value entry for every token, or imposing a fixed budget through a window
arXiv:2607.09073v1 Announce Type: new Abstract: Bayesian optimization routinely warm-starts a target experiment with data from related source tasks, and the multi-task Gaussian process is the textbook surrogate for the job. We revisit this default in a controlled setting and find that it misestimate
arXiv:2607.08778v1 Announce Type: cross Abstract: Alzheimer's Disease (AD) is a complex neurodegenerative disorder that continues to impact millions of people worldwide. Predicting AD conversion during the prodromal stage remains critical for disease understanding and patient care. As such, survival
arXiv:2607.08332v1 Announce Type: new Abstract: Financial markets are noisy, non-stationary, and high-dimensional, making it difficult to discover predictive and robust trading signals. Alpha discovery has evolved from manual factor design to machine learning, evolutionary search, and recent LLM-bas
arXiv:2503.08394v5 Announce Type: replace-cross Abstract: Multi-task optimization is typically characterized by a fixed and finite set of tasks. The present paper relaxes this condition by considering a non-fixed and potentially infinite set of optimization tasks defined in a parameterized, continuo
arXiv:2512.16558v3 Announce Type: replace Abstract: Clustering is a cornerstone of modern data analysis. Detecting clusters in exploratory data analyses (EDA) requires algorithms that make few assumptions about the data. Density-based clustering algorithms are particularly well-suited for EDA becaus
arXiv:2607.08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures. Existing approaches optimi
arXiv:2607.07888v1 Announce Type: new Abstract: This paper studies distributed sketching for ordinary least squares (OLS) regression, an approach that distributes small sketches of a large data set over multiple machines to separately construct OLS estimators and average them. Unlike prior studies t
arXiv:2607.08109v1 Announce Type: new Abstract: We propose contrastive order learning (ConOrd), a contrastive learning framework for ordinal regression that integrates the strengths of contrastive learning and order learning. While contrastive learning effectively leverages all samples in a batch, i
arXiv:2603.16481v3 Announce Type: replace Abstract: Non-conservative uncertainty bounds are essential for making reliable predictions about latent functions from noisy data, and thus, a key enabler for safe learning-based control. In this domain, kernel methods such as Gaussian process regression ar
arXiv:2603.18078v2 Announce Type: replace Abstract: We present the Variational Phasor Circuit (VPC), a deterministic classical learning architecture on the continuous $S^1$ unit-circle manifold. Inspired by variational quantum circuits, VPC replaces dense weight matrices with trainable phase shifts,
arXiv:2607.07735v1 Announce Type: cross Abstract: Sparse precision matrix estimation provides an interpretable and computationally efficient framework for modeling conditional dependencies in high-dimensional, low-sample-size data. A recurring challenge is appropriately selecting the regularization
arXiv:2510.22052v2 Announce Type: replace Abstract: The field of artificial intelligence (AI) has taken a tight hold on broad aspects of society, industry, business, and governance in ways that dictate the prosperity and might of the world's economies. The AI market size is projected to grow from {\
arXiv:2607.08103v1 Announce Type: new Abstract: Rank estimation under label noise poses a fundamental challenge, as ordinal annotations often exhibit structured uncertainty rather than simple label corruption. In this paper, we reformulate rank estimation with noisy ordinal labels as a stochastic or
arXiv:2607.08581v1 Announce Type: new Abstract: Extreme Learning Machine (ELM) computes output weights analytically using the Moore-Penrose pseudoinverse. Although this leads to fast training, its numerical stability depends strongly on the conditioning of the hidden layer matrix. This paper studies
arXiv:2603.23318v2 Announce Type: replace Abstract: Among the different possible strategies for evaluating the reliability of individual predictions of classifiers, robustness quantification stands out as a method that evaluates how much uncertainty a classifier could cope with before changing its p
arXiv:2606.01374v2 Announce Type: replace Abstract: Observable performance is commonly used to characterize biological systems. In adaptive systems, however, similar performances may arise from distinct organizations, and configurations that appear comparable at a given time may follow different lon
arXiv:2607.01283v1 Announce Type: cross Abstract: Grid-based approaches to approximate nearest neighbor (ANN) search have been absent from modern scaling analyses. We present a systematic characterization of a multiprobe grid algorithm with respect to dataset size $N$ and dimensionality $d$. Our exp
arXiv:2607.01520v1 Announce Type: new Abstract: Transformer inference on long sequences is expensive because softmax attention repeatedly reads from a large KV cache. The prevalent approach to this bottleneck is KV cache compression, which replaces the full cache with a compact summary. Despite its
arXiv:2607.01498v1 Announce Type: new Abstract: We investigate the problem of learning useful policy representations (embeddings) in two-player zero-sum imperfect-information games. We make three contributions: First, we introduce methods of creating datasets of policies for a given game. Second, we
arXiv:2607.01752v1 Announce Type: new Abstract: Temporal point processes (TPPs) have widespread applications across various domains. Compared to modeling the conditional intensity of a TPP, modeling its cumulative conditional intensity function (CCIF) improves computational efficiency and eliminates
arXiv:2607.01527v1 Announce Type: cross Abstract: Room embeddings derived from reverberant speech are often unreliable: speech content and recording degradation can alter the representation even when speaker, room, and source-receiver geometry remain unchanged, degrading downstream task performance.
arXiv:2607.02212v1 Announce Type: cross Abstract: Aqueous solubility is a key property in early-stage drug discovery, but most predictive models merge physicochemical descriptors and molecular graph information into a single representation, obscuring whether a prediction is driven by global chemistr
arXiv:2607.01185v1 Announce Type: new Abstract: Combinatorial optimization (CO) problems are difficult because certifiable discrete structure induces exponential search. One needs to search over the set exponentially many candidates to certify optimality, however, the structural feasibility of a pat
arXiv:2606.15054v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) detect features via inner product, so a feature's activation scales with both its directional alignment and the input's norm. Features that fire on token norm therefore claim dictionary slots regardless of content alignme
arXiv:2507.14023v2 Announce Type: replace-cross Abstract: Regression problems with bounded continuous outcomes frequently arise in statistical and machine learning applications, such as the analysis of rates and proportions. A central challenge in this setting is predicting the response at a new cov
arXiv:2606.30358v1 Announce Type: cross Abstract: We design an algorithm for learning the coefficients of an $n$-qubit constant-local Lindbladian to $\varepsilon$ error with $O(g d^2 \log(n) / \varepsilon^2)$ total evolution time, where $g$ is the single-site energy and $d$ is the (approximate) degr
arXiv:2606.29440v1 Announce Type: new Abstract: Repeatedly solving parametric PDEs is essential for uncertainty quantification, design optimization and inverse problems, but conventional neural operators require expensive non-convex training. We introduce PCA--RaNN, a randomized latent neural operat
arXiv:2605.03065v4 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. This work introduces Off-policy Generative Policy Optimization (OGPO), a sample-efficient algori
arXiv:2604.25241v2 Announce Type: replace Abstract: Categorical structural optimization under aleatoric uncertainty is challenging because each design variable must be selected from a finite catalog of admissible instances, while each candidate design may require expensive stochastic finite-element
arXiv:2606.00827v3 Announce Type: replace-cross Abstract: Strategic classification (SC) investigates scenarios where agents manipulate their features to obtain favorable decisions from predictive models. Existing fairness-aware SC approaches primarily focus on group fairness and typically assume tha
arXiv:2606.26418v1 Announce Type: new Abstract: A non-agentic "oracle" AI that estimates probabilities of future events faces a self-reference problem: once its answer is learned and acted upon, it can change the very probability it was asked to report. One response, advocated for the Scientist AI p
arXiv:2606.27014v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) have recently emerged as a promising paradigm for world modeling by learning predictive dynamics in a latent space rather than generating future observations at the input level. Despite their empirical s
arXiv:2606.27359v1 Announce Type: cross Abstract: Many decoding methods for large language models can be understood as shifting probability mass toward outputs that are more likely under the model, either locally at the token level or globally at the sequence level. Therefore, their success depends
arXiv:2606.27096v1 Announce Type: new Abstract: Transformer-based models have recently attracted increasing attention for Raman spectral classification. In this study, a transformer-based approach was systematically evaluated using a nested leave-one-replicate-out cross-validation framework and comp
arXiv:2606.27326v1 Announce Type: new Abstract: Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fluent while drifting from the ground-truth dynamics. We hypothesize that hallucination concentrates in
arXiv:2606.24084v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student policy using teacher signals computed on trajectories sampled by the student itself. Recent work shows that sampled-token OPD can be fragile on long-horizon reasoning tasks and that local teacher-support
arXiv:2606.24900v1 Announce Type: new Abstract: This paper proposes a new approach to near-sensor computing, in which a lightweight Neural Architecture Search (NAS) is performed directly on the deployment device to find the best tiny neural architecture for analyzing the real-time data acquired thro
arXiv:2606.26027v1 Announce Type: new Abstract: Tool use enables large language models (LLMs) to perform complex tasks, and recent agentic reinforcement learning (RL) methods show promise for enhancing model capabilities. However, RL alone often leads to instability or limited gains in tool-use task
arXiv:2606.24974v1 Announce Type: new Abstract: Explainability techniques are used to assess the output of various deep learning models. This is especially true in healthcare, where models need to be trusted and decisions justified. Explainability (XAI) tools use heuristics which often add signal no
arXiv:2606.25978v1 Announce Type: cross Abstract: Multi-agent goal recognition asks an observer to jointly infer which agents act together and what each team is trying to achieve, so the hypothesis space grows combinatorially with the number of team partitions and goals per team. Real applications s
arXiv:2606.23856v2 Announce Type: replace Abstract: Generative molecular models for drug design are a promising direction with much active research. In the next phase of computational drug design, such models will need to understand small molecule structure and protein-ligand interactions, and they
arXiv:2504.06138v3 Announce Type: replace-cross Abstract: Professional users need tools to help them gain actionable insights from large multimedia collections. Foundation models and AI agents have rapidly changed the playing field, and improving their accuracy, trustworthiness, and reasoning capabi
arXiv:2603.13343v3 Announce Type: replace-cross Abstract: Predictive maintenance for connected vehicles offers the potential to reduce unexpected breakdowns and improve fleet reliability, but most existing systems rely exclusively on internal diagnostic signals and are validated on simulated or indu
arXiv:2605.19178v2 Announce Type: replace-cross Abstract: The great success of neural networks primarily arises from the presence of the large number of weight parameters combined with nonlinearities in the input-output relationship of single neurons. In this work, we study the relationship between
arXiv:2606.22406v2 Announce Type: replace Abstract: Attention mechanisms have demonstrated remarkable empirical success in identifying relevant information from large collections of tokens, yet the theoretical principles underlying this behavior remain poorly understood. We study a stylized softmax-
arXiv:2606.19920v1 Announce Type: cross Abstract: Distributed optimization is a highly scalable and structurally transparent technique to solve multi-agent robotics problems; however, such methods often suffer from the need for highly-specialized, problem-specific hyperparameter tunings. In this wor
arXiv:2606.19853v1 Announce Type: new Abstract: We introduce SEA-PINN, a novel architecture that incorporates a Squeeze-Excitation-like attention mechanism into physics-informed neural networks to dynamically recalibrate the importance of neurons across layers. A key feature of SEA-PINN is its highl
arXiv:2606.20299v1 Announce Type: cross Abstract: Deep learning has managed to evade numerous intuitions from classical statistics to achieve unprecedented performance on a number of real-world tasks. In this article, we investigate the key features and surprises of deep learning from a physics-info
arXiv:2601.02322v2 Announce Type: replace-cross Abstract: A common approach to out-of-distribution prediction restricts models to causal or invariant covariates to avoid spurious associations that may change across environments. Despite its theoretical appeal, this strategy can underperform empirica
arXiv:2606.18997v1 Announce Type: new Abstract: Uncovering the true informational architecture of real-world complex systems requires disentangling how their components uniquely store, redundantly share, and synergistically integrate information over time. Integrated Information Decomposition ($\Phi
arXiv:2604.04342v2 Announce Type: replace Abstract: Many data-driven decision problems are formulated using a nominal distribution estimated from historical data, while performance is ultimately determined by a deployment distribution that may be shifted, context-dependent, partially observed, or st
arXiv:2606.19302v1 Announce Type: cross Abstract: As deep learning for physical systems continues to grow in popularity, efforts to improve generalizability have primarily focused on designing architectures that embed physical constraints. However, for machine-learning surrogate climate models (emul
arXiv:2606.19255v1 Announce Type: new Abstract: Time series anomaly detection plays a crucial role in a wide range of real-world applications. Reconstruction-based methods have become the mainstream paradigm, but they suffer from over-generalization and under-generalization problems, which are chall
arXiv:2506.03802v2 Announce Type: replace Abstract: We introduce a learning problem in a generalized two-sided matching market, where agents select actions to interact with their match. Specifically, we consider a setting in which matched agents engage in zero-sum games with initially unknown payoff
arXiv:2505.17740v2 Announce Type: replace Abstract: Making accurate predictions of chaotic time series is a complex challenge. Reservoir computing, a neuromorphic-inspired approach, has emerged as a powerful tool for this task. It exploits the memory and nonlinearity of dynamical systems without req
arXiv:2505.23939v2 Announce Type: replace Abstract: This paper presents an automatic method for the design of Neural Networks (NNs) at the edge, enabling Machine Learning (ML) access even in privacy-sensitive Internet of Things (IoT) applications. The proposed method runs on IoT gateways and designs
arXiv:2606.14954v1 Announce Type: cross Abstract: We develop a general framework for analyzing representation costs of parametric data-fitting methods through their parameter-space regularizers. From this abstract perspective, we define representation costs for arbitrary parametric models and reveal
arXiv:2606.03085v2 Announce Type: replace-cross Abstract: Causal tracing systematically intervenes on a large language model's (LLM's) internal representations to uncover and quantify the causal pathways linking specific inputs or computations to specific metrics of interest, quantifying the LLM's b