搜索结果：interventions

Language models perform a wide range of tasks at varying levels of abstraction with the capacity to flexibly infer tasks from context, execute multiple tasks simultaneously, and select among competing tasks. To study the role of model components in task behaviour, their causal influence can be investigated through interventions. Prior work on model steering has largely focused on interventions along global directions in activation space, modeling task representations as approximately linear and additive. By studying interventions at the neuron level, we find substantial, neuron-specific nonlinear effects on model outputs that are not captured by current steering approaches. We introduce Distributed Sparse Interventions (DSI), an intervention approach that considers nonlinearities and interactions between neurons across layers to identify sparse sets of neurons that elicit task-relevant computations. Across a range of tasks, we demonstrate that DSI can activate task behaviour in instruction-tuned language models by localising and intervening on as few as 0.01% of neurons, highlighting the effectiveness of sparse, distributed interventions in the neuron basis. Additionally, adopting

Non-pharmaceutical interventions (NPIs) are commonly used tools for controlling infectious disease transmission when pharmaceutical options are unavailable. Yet, identifying effective interventions that minimize societal disruption remains challenging. Agent-based simulation is a popular tool for analyzing the impact of possible interventions in epidemiology. However, automatically optimizing NPIs using agent-based simulations poses a complex problem because, in agent-based epidemiological models, interventions can target individuals based on multiple attributes, affect hierarchical group structures (e.g., schools, workplaces, and families), and be combined arbitrarily, resulting in a very large or even infinite search space. We aim to support decision-makers with our Agent-based Infectious Disease Intervention Optimization System (ADIOS) that optimizes NPIs for infectious disease simulations using Grammar-Guided Genetic Programming (GGGP). The core of ADIOS is a domain-specific language for expressing NPIs in agent-based simulations that structures the intervention search space through a context-free grammar. To make optimization more efficient, the search space can be further red

Human interventions are a common source of supervision in autonomous systems during deployment. Many existing approaches are based on avoiding interventions, yet the consequences of this objective are not well understood. We develop a geometric perspective on intervention learning that characterizes intervention avoidance as constraining policies to a face of the occupancy measure polytope. This view reveals that the effectiveness of intervention learning depends on the informativeness of the intervention strategy: highly informative interventions uniquely determine the solution, while weak interventions leave a large set of feasible policies, many of which are suboptimal. Motivated by this under-specification, we define Robust Intervention Learning (RIL) as the problem of learning policies that perform well under varying levels of intervention informativeness. From the geometric formulation, we derive Residual Intervention Fine-Tuning (RIFT), which combines interventions with a prior policy to select among feasible solutions. We show that RIFT provides provable improvement over the prior and corresponds to solving a constrained reinforcement learning problem with an induced reward

Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely developing independently. In practice, multiple interventions must be applied sequentially to the same model, yet we lack standardized ways to study how interventions interact. We fill this gap by introducing composable interventions, a framework to study the effects of using multiple interventions on the same language models, featuring new metrics and a unified codebase. Using our framework, we conduct extensive experiments and compose popular methods from three emerging intervention categories -- Knowledge Editing, Model Compression, and Machine Unlearning. Our results from 310 different compositions uncover meaningful interactions: compression hinders editing and unlearning, composing interventions hinges on their order of application, and popular general-purpose metrics are inadequate for assessing composability. Taken together, our findings showcase clear gaps in composability, suggesting a need for new multi-objective interventions. All of our

It is recognised that treatment-related clustering should be allowed for in the sample size and analyses of individually-randomised parallel-group trials that evaluate therapist-delivered interventions such as psychotherapy. Here, interventions are a treatment factor, but therapists are not. If the aim of a trial is to separate effects of therapists from those of interventions, we propose that interventions and therapists should be regarded as two potentially interacting treatment factors (one fixed, one random) with a factorial structure. We consider the specific design where each therapist delivers each intervention (crossed therapist-intervention design), and the resulting therapist-intervention combinations are randomised to patients. We adopt a classical Design of Experiments (DoE) approach to propose a family of orthogonal factorial designs and their associated data analyses, which allow for therapist learning and centre too. We set out the associated data analyses using ANOVA and regression and report the results of a small simulation study conducted to explore the performance of the proposed randomisation methods in estimating the intervention effect and its standard error,

Prescriptive Process Monitoring (PresPM) recommends interventions during running business processes to optimize key performance indicators (KPIs). In realistic settings, interventions are rarely isolated: organizations need to align sequences of interventions to jointly steer the outcome of a case. Existing PresPM approaches only partially address this challenge. Many focus on a single intervention decision, while others treat multiple interventions independently, ignoring how they interact over time. Methods that do address these dependencies depend either on simulation or data augmentation to approximate the process to train a Reinforcement Learning (RL) agent, which may create a reality gap and introduce bias. We introduce SCOPE (Sequential Causal Optimization of Process Interventions), a PresPM approach that learns aligned sequential intervention recommendations. SCOPE employs backward induction to estimate the effect of each candidate intervention action, propagating its impact from the final decision point back to the first. By leveraging causal learners, our method can utilize observational data directly, unlike methods that require constructing process approximations for RL

The deployment of biased machine learning (ML) models has resulted in adverse effects in crucial sectors such as criminal justice and healthcare. To address these challenges, a diverse range of machine learning fairness interventions have been developed, aiming to mitigate bias and promote the creation of more equitable models. Despite the growing availability of these interventions, their adoption in real-world applications remains limited, with many practitioners unaware of their existence. To address this gap, we systematically identified and compiled a dataset of 62 open source fairness interventions and identified active ones. We conducted an in-depth analysis of their specifications and features to uncover considerations that may drive practitioner preference and to identify the software interventions actively maintained in the open source ecosystem. Our findings indicate that 32% of these interventions have been actively maintained within the past year, and 50% of them offer both bias detection and mitigation capabilities, mostly during inprocessing.

Selective conformal prediction can yield substantially tighter uncertainty sets when we can identify calibration examples that are exchangeable with the test example. In interventional settings, such as perturbation experiments in genomics, exchangeability often holds only within subsets of interventions that leave a target variable "unaffected" (e.g., non-descendants of an intervened node in a causal graph). We study the practical regime where this invariance structure is unknown and must be estimated from data. Our main result quantifies how coverage degrades when the estimated safe calibration set accidentally includes interventions that affect the target, and gives a conservative correction when an upper bound on this error is available. Rather than learning a full causal graph, we learn only the intervention-target relationships needed to choose calibration interventions. We give algorithms for this partial learning task and evaluate them on synthetic structural equation models and Replogle K562 CRISPR-interference data, where the experiments illustrate synthetic gains from selective calibration and finite-sample tradeoffs on real perturbation screens.

Causal graph discovery is a significant problem with applications across various disciplines. However, with observational data alone, the underlying causal graph can only be recovered up to its Markov equivalence class, and further assumptions or interventions are necessary to narrow down the true graph. This work addresses the causal discovery problem under the setting of stochastic interventions with the natural goal of minimizing the number of interventions performed. We propose the following stochastic intervention model which subsumes existing adaptive noiseless interventions in the literature while capturing scenarios such as fat-hand interventions and CRISPR gene knockouts: any intervention attempt results in an actual intervention on a random subset of vertices, drawn from a distribution dependent on attempted action. Under this model, we study the two fundamental problems in causal discovery of verification and search and provide approximation algorithms with polylogarithmic competitive ratios and provide some preliminary experimental results.

Estimating causal effects of joint interventions on multiple variables is crucial in many domains, but obtaining data from such simultaneous interventions can be challenging. Our study explores how to learn joint interventional effects using only observational data and single-variable interventions. We present an identifiability result for this problem, showing that for a class of nonlinear additive outcome mechanisms, joint effects can be inferred without access to joint interventional data. We propose a practical estimator that decomposes the causal effect into confounded and unconfounded contributions for each intervention variable. Experiments on synthetic data demonstrate that our method achieves performance comparable to models trained directly on joint interventional data, outperforming a purely observational estimator.

Despite the multifaceted recent advances in interventional causal representation learning (CRL), they primarily focus on the stylized assumption of single-node interventions. This assumption is not valid in a wide range of applications, and generally, the subset of nodes intervened in an interventional environment is fully unknown. This paper focuses on interventional CRL under unknown multi-node (UMN) interventional environments and establishes the first identifiability results for general latent causal models (parametric or nonparametric) under stochastic interventions (soft or hard) and linear transformation from the latent to observed space. Specifically, it is established that given sufficiently diverse interventional environments, (i) identifiability up to ancestors is possible using only soft interventions, and (ii) perfect identifiability is possible using hard interventions. Remarkably, these guarantees match the best-known results for more restrictive single-node interventions. Furthermore, CRL algorithms are also provided that achieve the identifiability guarantees. A central step in designing these algorithms is establishing the relationships between UMN interventional

Artificial intelligence (AI)-enabled digital interventions, including Generative AI (GenAI) and Human-Centered AI (HCAI), are increasingly used to expand access to digital psychiatry and mental health care. This PRISMA-ScR scoping review maps the landscape of AI-driven mental health (mHealth) technologies across five critical phases: pre-treatment (screening/triage), treatment (therapeutic support), post-treatment (remote patient monitoring), clinical education, and population-level prevention. We synthesized 36 empirical studies implemented through early 2024, focusing on Large Language Models (LLMs), machine learning (ML) models, and autonomous conversational agents. Key use cases involve referral triage, empathic communication enhancement, and AI-assisted psychotherapy delivered via chatbots and voice agents. While benefits include reduced wait times and increased patient engagement, we address recurring challenges like algorithmic bias, data privacy, and human-AI collaboration barriers. By introducing a novel four-pillar framework, this review provides a comprehensive roadmap for AI-augmented mental health care, offering actionable insights for researchers, clinicians, and poli

Sparse Autoencoders (SAEs) decompose residual-stream activations into interpretable features. Recent latent-space defenses increasingly rely on these decompositions, assuming that identified "unsafe" SAE features serve as actionable handles for monitoring and intervention. In this paradigm, clamping a specific harmful feature is expected to reliably prevent model misbehavior. However, we show that this success may hide a recoverable failure mode: the clamp may block one visible route to a behavior without eliminating the behavior itself. We formulate this vulnerability as post-intervention recovery, a constrained residual-space optimization problem. Starting from the post-intervention residual state, we optimize residual perturbations to recover the pre-intervention behavior while preserving the post-intervention values of the targeted SAE features. Even under a strong threat model where the intervention remains active throughout optimization and generation, recovery remains possible. To rule out that recovery simply undoes the intervention, we use encoder-orthogonal updates for single-layer interventions and the corresponding feature-map Jacobian in the cross-layer setting. Across

Recent conversations in the algorithmic fairness literature have raised several concerns with standard conceptions of fairness. First, constraining predictive algorithms to satisfy fairness benchmarks may lead to non-optimal outcomes for disadvantaged groups. Second, technical interventions are often ineffective by themselves, especially when divorced from an understanding of structural processes that generate social inequality. Inspired by both these critiques, we construct a common decision-making model, using mortgage loans as a running example. We show that under some conditions, any choice of decision threshold will inevitably perpetuate existing disparities in financial stability unless one deviates from the Pareto optimal policy. Then, we model the effects of three different types of interventions. We show how different interventions are recommended depending upon the difficulty of enacting structural change upon external parameters and depending upon the policymaker's preferences for equity or efficiency. Counterintuitively, we demonstrate that preferences for efficiency over equity may lead to recommendations for interventions that target the under-resourced group. Finally

Hierarchical reinforcement learning (HRL) improves the efficiency of long-horizon reinforcement-learning tasks with sparse rewards by decomposing the task into a hierarchy of subgoals. The main challenge of HRL is efficient discovery of the hierarchical structure among subgoals and utilizing this structure to achieve the final goal. We address this challenge by modeling the subgoal structure as a causal graph and propose a causal discovery algorithm to learn it. Additionally, rather than intervening on the subgoals at random during exploration, we harness the discovered causal model to prioritize subgoal interventions based on their importance in attaining the final goal. These targeted interventions result in a significantly more efficient policy in terms of the training cost. Unlike previous work on causal HRL, which lacked theoretical analysis, we provide a formal analysis of the problem. Specifically, for tree structures and, for a variant of Erdős-Rényi random graphs, our approach results in remarkable improvements. Our experimental results on HRL tasks also illustrate that our proposed framework outperforms existing work in terms of training cost.

Counterfactual reasoning allows us to explore hypothetical scenarios in order to explain the impacts of our decisions. However, addressing such inquires is impossible without establishing the appropriate mathematical framework. In this work, we introduce the problem of counterfactual reasoning in the context of vector autoregressive (VAR) processes. We also formulate the inference of a causal model as a joint regression task where for inference we use both data with and without interventions. After learning the model, we exploit linearity of the VAR model to make exact predictions about the effects of counterfactual interventions. Furthermore, we quantify the total causal effects of past counterfactual interventions. The source code for this project is freely available at https://github.com/KurtButler/counterfactual_interventions.

In 2017, GitHub was the first online open source platform to show security alerts to its users. It has since introduced further security interventions to help developers improve the security of their open source software. In this study, we investigate and compare the effects of these interventions. This offers a valuable empirical perspective on security interventions in the context of software development, enriching the predominantly qualitative and survey-based literature landscape with substantial data-driven insights. We conduct a time series analysis on security-altering commits covering the entire history of a large-scale sample of over 50,000 GitHub repositories to infer the causal effects of the security alert, security update, and code scanning interventions. Our analysis shows that while all of GitHub's security interventions have a significant positive effect on security, they differ greatly in their effect size. By comparing the design of each intervention, we identify the building blocks that worked well and those that did not. We also provide recommendations on how practitioners can improve the design of their interventions to enhance their effectiveness.

This article provides resources to design effective diversity, equity and inclusion (DEI) interventions in physics settings. It summarizes critiques of DEI interventions and reviews research findings suggesting that DEI interventions show modest but positive benefits. It covers physics-specific concerns around DEI (resistance from skeptical participants, unintended negative consequences for members of minoritized groups). The article then explores six design questions: 1) What are the intended outcomes of the intervention? (with a list of possible outcomes) 2) How will the intervention be justified to participants? 3) Will the intervention be voluntary or required? 4) Who will the participants be? 5) What activities will the intervention consist of? (with suggested activities paired to outcomes) 6) How will you know whether the intervention worked? (with tools used by other researchers to measure particular outcomes, and bonus suggestions for how to carry out publication-worthy evaluations). Each question is explored using research results and recommendations, and illustrated using examples from physics and other STEM settings.