论文检索

Social Aspects · Accountability, Transparency and Interpretability

Zhengfu He, Junxuan Wang, Rui Lin, Xuyang Ge, Wentao Shu, Qiong Tang, Junping Zhang, Xipeng Qiu

We propose Low-Rank Sparse Attention (Lorsa), a sparse replacement model of Transformer attention layers to disentangle original Multi Head Self Attention (MHSA) into individually comprehensible components. Lorsa is designed to address the challenge of \textit{attention superposition} to understand attention-mediated interaction between features in different token positions. Lorsa helps find cleaner and finer-grained versions of previously discovered MHSA behaviors like induction heads, successor heads, attention sink, and a comprehensive family of arithmetic-specific Lorsa heads. Interestingly, we identify a novel head type called \emph{subtoken induction heads} that function at character level rather than token level. Automated interpretability analysis indicates that Lorsa achieves parity with SAE in interpretability while Lorsa exhibits superior circuit discovery properties. We also conduct extensive experiments on architectural design ablation, correlation to original MHSA heads and error analysis. Our early attempt to fully sparsify a toy Transformer succeeds to reveal clean global circuits. Eventually, we hope Lorsa would help us greatly understand attention computation and enable full sparsification of model computation along with its MLP counterparts. Lorsa is open-sourced at https://anonymous.4open.science/r/Lorsa-5686/.

Deep Learning · Algorithms

Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Xudong Wang, Zhenzhen Huang, Pengcheng Zheng, Shuai Yuan, Sheng Zheng, Qigan Sun, Jie Zou 等

Chain-of-Thought (CoT) has been shown to significantly improve the reasoning accuracy of large language models (LLMs) on complex tasks. However, due to the autoregressive, step-by-step generation paradigm, existing CoT methods suffer from two fundamental limitations. First, the reasoning process is highly susceptible to early-stage errors, which tend to propagate and amplify without a global coordination and correction mechanism, thereby distorting the overall reasoning chain. Second, current CoT methods lack structured analytical frameworks for pruning redundant reasoning and identifying critical reasoning features, resulting in instability and reduced interpretability. To address these issues, we propose Global Hypothesis Structure via Topological Data Analysis (GHS-TDA), which constructs a semantically enriched global hypothesis graph that integrates and coordinates multiple candidate reasoning paths, thereby supporting global consistency refinement and error mitigation. GHS-TDA applies persistent homology-based topological data analysis to capture stable multi-scale structures, remove redundancy and inconsistencies, and extract a more reliable reasoning skeleton. By jointly leveraging reasoning diversity and topological stability, GHS-TDA achieves self-adaptive convergence, produces high-confidence and interpretable reasoning paths, and consistently outperforms strong baselines in terms of both accuracy and robustness across multiple reasoning benchmarks.

Jerry Yao-Chieh Hu, Hude Liu, Jennifer Zhang, Han Liu

We prove that a minimal Transformer with frozen weights emulates a broad class of algorithms by in-context prompting. We formalize two modes of in-context algorithm emulation. In the *task-specific mode*, for any continuously differentiable function $f: \mathbb{R} \to \mathbb{R}$, we construct a single-head softmax attention layer whose forward pass reproduces functions of the form $f(w^\top x - y)$ to arbitrary precision. This general template subsumes many popular machine learning algorithms (e.g., gradient descent, linear regression, ridge regression). In the *prompt-programmable mode*, we prove universality: a single fixed-weight two-layer softmax attention module emulates all algorithms from the task-specific class (i.e., each implementable by a single softmax attention) via only prompting. Our key idea is to construct prompts that encode an algorithm’s parameters into token representations, creating sharp dot-product gaps that force the softmax attention to follow the intended computation. This construction requires no feed-forward layers and no parameter updates. All adaptation happens through the prompt alone. Numerical results corroborate our theory. These findings forge a direct link between in-context learning and algorithmic emulation, and offer a simple mechanism for large Transformers to serve as prompt-programmable interpreters of algorithms. They illuminate how GPT-style foundation models may swap algorithms via prompts alone, and establish a form of algorithmic universality in modern Transformer models.

Optimization · Everything Else

Ni Zhang, Zhiguang Cao, Jianan Zhou, Cong Zhang, Yew-Soon Ong

Complex vehicle routing problems (VRPs) remain a fundamental challenge, demanding substantial expert effort for intent interpretation and algorithm design. While large language models (LLMs) offer a promising path toward automation, current approaches still rely on external intervention, which restrict autonomy and often lead to execution errors and low solution feasibility. To address these challenges, we propose an Agentic Framework with LLMs (AFL) for solving complex vehicle routing problems, achieving full automation from problem instance to solution. AFL directly extracts knowledge from raw inputs and enables self-contained code generation without handcrafted modules or external solvers. To improve trustworthiness, AFL decomposes the overall pipeline into three manageable subtasks and employs four specialized agents whose coordinated interactions enforce cross-functional consistency and logical soundness. Extensive experiments on 60 complex VRPs, ranging from standard benchmarks to practical variants, validate the effectiveness and generality of our framework, showing comparable performance against meticulously designed algorithms. Notably, it substantially outperforms existing LLM-based baselines in both code reliability and solution feasibility, achieving rates close to 100% on the evaluated benchmarks.

Deep Learning · Generative Models and Autoencoders

Yuxin Liu, Kaiming Wang, Chenguang Yang, Yulia Gel, Yuzhou Chen

Spatio-temporal point process (STPP) data appear in many domains. A natural way to model them is to describe how the instantaneous event rate varies over space and time given the observed history which enables interpretation, interaction detection, and forecasting. Traditional parametric kernel-based models, while historically dominant, struggle to capture complex nonlinear patterns. In contrast, deep learning methods leverage the representational power of neural networks to aggregate historical events and integrate spatio-temporal point processes. However, existing deep learning methods often process space and time independently, overlooking the spatio-temporal dependencies. To address this limitation, we propose a novel method called Topology-ENhanced Diffusion Model (TEN-DM), including two key components namely spatio-temporal graph construction and multimodal topological feature representation learning. Further, we use temporal query technique to effectively capture periodic temporal patterns for learning effective temporal representations. Extensive experiments show the effectiveness of TEN-DM on multiple STPP datasets compared to state-of-the-art methods.

Social Aspects · Accountability, Transparency and Interpretability

Wengang Li, Lingqi Zhang, Toshio Endo, Mohamed Wahib

Mixture-of-Experts (MoE) has been a prevalent method for scaling up large language models at a reduced computational cost. Despite its effectiveness, the routing mechanism of MoE still lacks a clear understanding from the perspective of cross-layer mechanistic interpretability. We propose a light-weight methodology at which we can break down the routing decision for MoE to the contribution of model components, in a recursive fashion. We use our methodology to dissect the routing mechanism by decomposing the input of routers into model components. We study how different model components contribute to the routing in different widely used open models. Our findings on four different LLMs reveal patterns such as: a) MoE layer outputs usually contribute more than attention layer outputs to the routing decisions of subsequent layers, b) *MoE entanglement* at which MoE firing up in layers consistently correlate with firing up of MoE in subsequent layers, and c) some components can persistently influence the routing in many following layers. Our study also includes findings on how different models have different patterns when it comes to long-range and short-range inhibiting/promoting effects that components can have over MoE in subsequent layers. Our results indicate the importance of quantifying the impact of components across different layers on MoE to understand the routing mechanism.

Applications · Robotics

Yuqi Ye, Zijian Zhang, Junhong Lin, Shangkun Sun, Changhao Peng, Wei Gao

Vision-language models (VLMs) are increasingly being adopted for end-to-end autonomous driving systems due to their exceptional performance in handling long-tail scenarios. However, current VLM-based approaches suffer from two major limitations: 1) Some VLMs directly output planning results without chain-of-thought (CoT) reasoning, bypassing crucial perception and prediction stages which creates a significant domain gap and compromises decision-making capability; 2) Other VLMs can generate outputs for perception, prediction, and planning tasks but employ a fragmented decision-making approach where these modules operate seperately, leading to a significant lack of synergy that undermines true planning performance. To address these limitations, we propose ${AutoDrive\text{-}P^3}$, a novel framework that seamlessly integrates $\underline{\textbf{P}}$erception, $\underline{\textbf{P}}$rediction, and $\underline{\textbf{P}}$lanning through structured reasoning. We introduce the ${P^3\text{-}CoT}$ dataset to facilitate coherent reasoning and propose ${P^3\text{-}GRPO}$, a hierarchical reinforcement learning algorithm that provides progressive supervision across all three tasks. Specifically, ${AutoDrive\text{-}P^3}$ progressively generates CoT reasoning and answers for perception, prediction, and planning, where perception provides essential information for subsequent prediction and planning, while both perception and prediction collectively contribute to the final planning decisions, enabling safer and more interpretable autonomous driving. Additionally, to balance inference efficiency with performance, we introduce dual thinking modes: detailed thinking and fast thinking. Extensive experiments on both open-loop (nuScenes) and closed-loop (NAVSIMv1/v2) benchmarks demonstrate that our approach achieves state-of-the-art performance in planning tasks. Code is available at https://github.com/haha-yuki-haha/AutoDrive-P3, https://openi.pcl.ac.cn/OpenAIDriving/AutoDrive-P3.

Computer Vision · Vision Models & Multimodal

Bhuvan Aggarwal, Amit More, Mudit Soni, Srinivasa Divakar Bhat

Understanding the negation in a sentence is an important part of compositional understanding and logic in natural language. Many practical AI applications, such as autonomous driving, include precise instruction with negations. For example, following instruction to an AI assistant ”locate a parking spot without a vehicle” requires the assistant to not confuse between presence and absence of vehicles. Al- though joint embedding-based Vision Language Models (VLMs) like CLIP have revolutionized multi-modal tasks, they struggle to interpret negation. To address this limitation, recently many works proposed to solve the problem through a data- centric approach by introducing additional datasets with hard-negative samples for both image and text data. Contrary to these approaches, we present a zero-shot approach to tackle the negation understanding problem. We probe the properties of CLIP text embeddings and show that they follow compositional arithmetic op- erations, which allow the addition or removal of semantic information directly in the embedding space. We then present a rule-based approach to extract negated text from given caption and then use it to explicitly remove corresponding se- mantic information from original embedding, improving negation understanding in VLMs. Our approach does not require expensive training process to induce negation understanding into the model, and achieves the state-of-the-art perfor- mance on popular benchmark for negation understanding. We improve baseline CLIP model performance on NegBench from 25.5% to 67.0% for MCQ and from 50.9% to 56.1% for retrieval tasks. Even NegCLIP model which is fine-tuned on negtion datasets, our approach boosts its MCQ accuracy from 54.03% to 66.22% and retrieval accuracy from 59.25% to 60.1% showing strong performance.

Theory · Everything Else

Juni Schindler, Mauricio Barahona

Datasets often possess an intrinsic multiscale structure with meaningful descriptions at different levels of coarseness. Such datasets are naturally described as multi-resolution clusterings, i.e., not necessarily hierarchical sequences of partitions across scales. To analyse and compare such sequences, we use tools from topological data analysis and define the Multiscale Clustering Bifiltration (MCbiF), a 2-parameter filtration of abstract simplicial complexes that encodes cluster intersection patterns across scales. The MCbiF is a complete invariant of (non-hierarchical) sequences of partitions and can be interpreted as a higher-order extension of Sankey diagrams, which reduce to dendrograms for hierarchical sequences. We show that the multiparameter persistent homology (MPH) of the MCbiF yields a finitely presented and block decomposable module, and its stable Hilbert functions characterise the topological autocorrelation of the sequence of partitions. In particular, at dimension zero, the MPH captures violations of the refinement order of partitions, whereas at dimension one, the MPH captures higher-order inconsistencies between clusters across scales. We then demonstrate through experiments the use of MCbiF Hilbert functions as interpretable topological feature maps for downstream machine learning tasks, and show that MCbiF feature maps outperform both baseline features and representation learning methods on regression and classification tasks for non-hierarchical sequences of partitions. We also showcase an application of MCbiF to real-world data of non-hierarchical wild mice social grouping patterns across time.

Social Aspects · Accountability, Transparency and Interpretability

Luke Guerdan, Justin Whitehouse, Kimberly Truong, Ken Holstein, Steven Wu

As Generative AI (GenAI) systems see growing adoption, a key concern involves the external validity of evaluations, or the extent to which they generalize from lab-based to real-world deployment conditions. Threats to the external validity of GenAI evaluations arise when the source sample of human raters and system outputs used to obtain a system quality estimate differs from the target distribution at deployment time. In this work, we propose a doubly-robust estimation framework designed to address this evaluation sampling bias. Key to our approach is the use of synthetic "persona" ratings -- produced by prompting an LLM evaluator (i.e., an LLM-as-a-judge) to behave as a human rater with specific sociodemographic characteristics. Our doubly-robust framework combines these informative yet imperfect persona ratings with human ratings obtained under evaluation sampling bias to produce statistically valid system quality estimates. In particular, we show that our approach yields valid system quality estimates when either: (i) a model trained to predict human ratings using persona ratings and source data observed under sampling bias, or (ii) a reweighting model that corrects for sampling bias is of sufficient quality. We validate our framework theoretically and via a novel Persona Simulation Framework (PSF) designed to systematically manipulate persona quality and the degree of evaluation sampling bias present in source data. Our work provides a principled foundation for combining imperfect persona ratings with human ratings observed under sampling bias to obtain valid system quality estimates.

Applications · Language, Speech and Dialog

Zheng Lian, Licai Sun, Lan Chen, Haoyu Chen, Zebang Cheng, Fan Zhang, Ziyu Jia, Ziyang Ma, Fei Ma, Xiaojiang Peng 等

Descriptive Multimodal Emotion Recognition (DMER) has garnered increasing research attention. Unlike traditional discriminative paradigms that rely on predefined emotion taxonomies, DMER aims to describe human emotional state using free-form natural language, enabling finer-grained and more interpretable emotion representations. However, this free-form prediction paradigm introduces new challenges regarding its evaluation. Previous works depend on ground-truth descriptions, but emotions are inherently tied to diverse human behaviors, and generating a comprehensive and accurate description is inherently demanding. Other researchers reformulate this problem into a more tractable human preference learning task, but pairwise preference annotation involves substantial manual effort. This leads to a question: *can we leverage multimodal LLMs (MLLMs) to achieve more cost-efficient preference annotation?* To answer this, we propose **EmoPrefer**, a pioneering work exploring the potential of LLMs in decoding human emotion preferences. Specifically, we construct the first emotion preference dataset, **EmoPrefer-Data**, featuring high-quality preference annotations from experts. Additionally, we introduce **EmoPrefer-Bench**, which evaluates the performance of various MLLMs and prompting techniques in preference prediction, while also revealing new strategies to enhance their performance. To the best of our knowledge, this is the first work exploring the capabilities of LLMs in understanding human emotion preferences. Our work advances the field of DMER and lays the foundation for more intelligent human-computer interaction. Our data and code are released at https://github.com/zeroQiaoba/AffectGPT/tree/master/EmoPrefer.

Yongchao Chen, Yueying Liu, Junwei Zhou, Yilun Hao, Jingquan Wang, Yang Zhang, Na Li, Chuchu Fan

Practical guidance on training Large Language Models (LLMs) to leverage Code Interpreter across diverse tasks remains lacking. We present R1-Code-Interpreter, an extension of a text-only LLM trained via multi-turn supervised fine-tuning (SFT) and reinforcement learning (RL) to autonomously generate multiple code queries during step-by-step reasoning. Unlike prior RL + tool-use efforts focused on narrow domains such as math or retrieval, we curate 144 diverse reasoning and planning tasks and show that training a general-purpose Code Interpreter across them presents significant challenges due to task heterogeneity and scarcity of effective samples. To address this, we introduce a multi-stage curriculum learning approach that partitions training samples by measured improvement potential. The RL training prioritizes samples with higher potential and gradually shifts to lower-potential ones, increasing the average RL gains from merely +3.4\% to +9.3\% across Qwen-2.5 models (3/7/14B). Our final model, R1-CI-14B, improves average accuracy on the 37 test tasks from 44.1\% to 72.4\%, outperforming text-only GPT-4o (58.6\%) and GPT-4o with Code Interpreter (70.9\%). Notably, R1-CI-14B also exhibits emergent self-checking behavior through code generation. Datasets, Codes, and Models are available at https://github.com/yongchao98/R1-Code-Interpreter and https://huggingface.co/yongchao98.

Theory · Interpretability and Visualization

Xingshu Chen, Yifeng Guo, Jin-Hong Du

Quantifying feature importance with valid statistical uncertainty is central to interpretable machine learning, yet classical model-agnostic methods often fail under feature correlation, producing unreliable attributions and compromising inference. Statistical approaches that address correlation through feature decorrelation have shown promise but remain restricted to $\ell_2$ loss, limiting their applicability across diverse machine learning tasks. We introduce Flow-Disentangled Feature Importance (FDFI), a model-agnostic framework that resolves these limitations by combining principled statistical inference with computational flexibility. FDFI leverages flow matching to learn flexible disentanglement maps that not only handle arbitrary feature distributions but also provide an interpretable pathway for understanding how importance is attributed through the data's correlation structure. The framework generalizes the decorrelation-based attribution to general differentiable loss functions, enabling statistically valid importance assessment for black-box predictors across regression and classification. We establish statistical inference theory, deriving semiparametric efficiency of FDFI estimators, which enables valid confidence intervals and hypothesis testing with Type I error control. Experiments demonstrate that FDFI achieves substantially higher statistical power than removal-based and conditional permutation approaches, while maintaining robust and interpretable attributions even under severe interdependence. These findings hold across synthetic benchmarks and a broad collection of real datasets spanning diverse domains.

Social Aspects · Accountability, Transparency and Interpretability

Michael Hanna, Emmanuel Ameisen

LLMs can perform seemingly planning-intensive tasks, like writing coherent stories or functioning code, without explicitly verbalizing a plan; however, the extent to which they implicitly plan is unknown. In this paper, we define *latent planning* as occurring when LLMs possess internal planning representations that (1) cause the generation of a specific future token or concept, and (2) shape preceding context to license said future token or concept. We study the Qwen-3 family (0.6B-14B) on simple planning tasks, finding that latent planning ability increases with scale. Models that plan possess features that represent a planned-for word like *accountant*, and cause them to output *an* rather than *a*; moreover, even the less-successful Qwen-3 4B-8B have nascent planning mechanisms. On the more complex task of completing rhyming couplets, we find that models often identify a rhyme ahead of time, but even large models seldom plan far ahead. However, we can elicit some planning that increases with scale when steering models towards planned words in prose. In sum, we offer a framework for measuring planning and mechanistic evidence of how models' planning abilities grow with scale.

Yongchao Chen, Jiefeng Chen, Rui Meng, Ji Yin, Na Li, Chuchu Fan, Chi Wang, Tomas Pfister, Jinsung Yoon

While integrating tools like Code Interpreter and Search has significantly enhanced Large Language Model (LLM) reasoning in models like ChatGPT Agent and Gemini-Pro, practical guidance on optimal tool use is lacking. The core challenge is effectively combining textual reasoning, coding, and search for diverse questions. In this paper, we propose Tool-Use Mixture (TUMIX), an ensemble framework that runs multiple agents in parallel, each employing distinct tool-use strategies and answer paths. Agents in TUMIX iteratively share and refine responses based on the question and previous answers. In experiments, TUMIX achieves significant gains over state-of-the-art tool-augmented and test-time scaling methods, delivering an average accuracy improvement of up to 3.55\% over the best baseline on Gemini-2.5-Pro and Gemini-2.5-Flash across key reasoning benchmarks, with near-equal inference costs. We find that agent diversity and quality are crucial and can be enhanced by using LLMs to auto-optimize agent designs. Furthermore, TUMIX can halt refinement upon reaching sufficient confidence, preserving performance at only 49\% of the inference cost. Further scaling can achieve higher performance, albeit at a greater cost.

Wenjie Du, Jiahui Zhang, Xuqiang Li, Sihan Wang, Zhengyang Zhou, Hongxin Xiang, Jun Xia, Ye Wei, Yang Wang

Molecular interactions are a common phenomenon in physical chemistry field, which could produce unexpected biochemical properties harmful to humans, such as drug-drug interactions. Machine learning has the potential to deliver rapid and accurate predictions. However, the complexity of molecular structures and the diversity of molecular interactions could undermine model prediction accuracy and hinder generalizability. In this context, identifying core invariant substructures (\textit{i.e.}, rationales) has become essential for enhancing interpretability and generalization. Despite notable efforts, existing models often neglect the molecular pairs’ modeling, leading to insufficient capture of interaction relationships. To address these limitations, we propose a novel framework, \textbf{I}nteraction-aware \textbf{I}nvariant \textbf{Mole}cular learning (I2Mole), for generalizable property prediction. I2Mole meticulously models atomic interactions such as hydrogen bonds by initially establishing indiscriminate connections between intermolecular atoms, which are subsequently refined using an improved graph information bottleneck theory tailored for merged graphs. To further enhance model generalization, we construct an environment codebook by environment subgraph of the merged graph. This approach not only could provide noise source for optimizing mutual information but also preserve the integrity of chemical semantic information. By comprehensively leveraging the information inherent in the merged graph, our model accurately captures core substructures and significantly enhances generalization capabilities. Extensive experimental validation demonstrates the efficacy and generalizability of I2Mole. The implementation code is available.

Theory · Interpretability and Visualization

Garrett Baker, George Wang, Jesse Hoogland, Vinayak Pathak, Daniel Murfet

We develop a linear response framework for interpretability that treats a neural network as a Bayesian statistical mechanical system. A small perturbation of the data distribution, for example shifting the Pile toward GitHub or legal text, induces a first-order change in the posterior expectation of an observable localized on a chosen component of the network. The resulting susceptibility can be estimated efficiently with local SGLD samples and factorizes into signed, per-token contributions that serve as attribution scores. We combine these susceptibilities into a response matrix whose low-rank structure separates functional modules such as multigram and induction heads in a 3M-parameter transformer.

Social Aspects · Accountability, Transparency and Interpretability

jacob drori, Luke Marks, Bryce Woodworth, Alex Cloud, Alexander Turner

Recently, OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep CoTs monitorable by training only against output monitors that do not have access to CoT. We show that such training can still cause obfuscated CoTs via two mechanisms. First, when a model is trained to produce a safe-looking output, that model may generalize to making its CoTs look safe. Second, since later tokens are conditioned on earlier ones, safe‑looking CoTs may increase the likelihood of safe outputs, causing safe-looking CoTs to be reinforced. We introduce two mitigations to address these two issues, which achieve a Pareto improvement in terms of monitorability and task performance compared to regular training. To our knowledge, we are the first to identify and mitigate these problems. Our work implies that preserving CoT monitorability is more difficult than previously thought; we suggest practical guidelines for AI developers to maintain monitorable CoTs.

General Machine Learning · Representation Learning

Yalan Qin, Guorui Feng

Multi-view clustering aims to segment the view-specific data into the corresponding clusters. There have been a large number of works for multi-view clustering in recent years. As representive methods in multi-view clustering, works built on the graph make use of a view-consistent and discriminative graph while utilizing graph partitioning for the final clustering results. Despite the achieved significant success, these methods usually construct full graphs and the efficiency is not well guaranteed for the multi-view datasets with large scales. To handle the large-scale data, multi-view clustering methods based on anchor have been developed by learning the anchor graph with smaller size. However, the existing works neglect the interpretability of multi-view clustering based on anchor from the probabilistic perspective. These methods also ignore analyzing the relationship between the input data and the final clustering results based on the assigned meaningful probability associations in a unified manner. In this work, we propose a novel method termed Unified and Efficient Multi-view Clustering from Probabilistic perspective(UEMCP). It aims to improve the explanation ability of multi-view clustering based on anchor from the probabilistic perspective in an end-to-end manner. It ensures the consistent inherent structures among these views by learning the common transition probability from data points to categories in one step. With the guidance of the common transition probability matrix from data points to categories, the soft label of data points can be achieved based on the common transition probability matrix from anchor points to categories in the learning framework. Experiments on different challenging multi-view datasets confirm the superiority of UEMCP compared with the representative ones.

General Machine Learning · Causality

Tommaso Mencattini, Riccardo Cadei, Francesco Locatello

Randomized Controlled Trials are one of the pillars of science; nevertheless, they rely on hand-crafted hypotheses and expensive analysis. Such constraints prevent causal effect estimation at scale, potentially anchoring on popular yet incomplete hypotheses. We propose to discover the unknown effects of a treatment directly from data. For this, we turn unstructured data from a trial into meaningful representations via pretrained foundation models and interpret them via a Sparse Auto Encoder. However, discovering significant causal effects at the neural level is not trivial due to multiple-testing issues and effects entanglement. To address these challenges, we introduce _Neural Effect Search_, a novel recursive procedure solving both issues by progressive stratification. After assessing the robustness of our algorithm on semi-synthetic experiments, we showcase, in the context of experimental ecology, the first successful unsupervised causal effect identification on a real-world scientific trial.