Counterfactual Evaluation

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 44% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 63

Jul 23, 2026stat.ME

Equilibrium Causal Digital Twins: Validation, Transport, and Identification Limits

Digital twins are often used to predict how a system would respond to an intervention. In systems with feedback, a twin must reproduce an equilibrium counterfactual, and a twin developed in one domain may fail after mechanisms change. We study when these predictions can be validated and transported. For equilibrium causal games, we give conditions on the mechanisms, equilibrium selection, and intervention design under which agreement with experimental distributions identifies the counterfactual of interest. We show why agreement of means and covariances is insufficient for distributional queries. We then introduce cyclic selection diagrams and derive criteria for direct reuse and for hybrid models that combine invariant source mechanisms with target information. An impossibility result constructs systems that agree under every experiment in a finite design but disagree on the target counterfactual, showing that validation requires structural assumptions. For linear models, we derive intervention requirements that depend on the mechanisms that changed, the observation model, and graph support. When point identification fails, we characterize the remaining range of query values. We also provide statistical tests for reconstructed means and covariances and illustrate the theory in synthetic feedback systems.

Faraz Dadgostari, Neda Nazemi

Department of Mechanical & Industrial Engineering, Montana State University · Gianforte School of Computing, Montana State University

Counterfactual Evaluation Structural Causal Models Causal Identifiability Digital Twins Causal Inference

Jul 19, 2026cs.CV

EditCLEVR: A Paired-Scene Intervention Benchmark for Compositional Faithfulness of Object-Centric Representations

Object-centric learning aims to represent scenes as objects whose properties can be reused in new combinations. Existing evaluations usually score segmentation, single-image factor prediction, or downstream accuracy, but these tests do not directly ask whether a per-object representation behaves correctly under a controlled semantic edit. We introduce EditCLEVR, a paired-scene intervention benchmark in which each example contains a before/after pair of CLEVR-style renders with the same object indices and scene layout, and either exactly one known attribute change on one known object or a no-edit re-render for drift measurement. The protocol includes probe-free diagnostics for representation-change localization and stability, together with probe-decoded semantic faithfulness metrics that test whether the predicted scene change matches the intended intervention across in-distribution and compositional out-of-distribution (OOD) suites, allowing code-space movement and decoded object-attribute correctness to be evaluated separately. We introduce the semantic metric Scene-Graph Intervention Accuracy (SGIA), which requires the full after-scene prediction to be correct and the only predicted before-to-after semantic change to be the intended object-factor edit. We also establish Delta-SGIA as a companion diagnostic that checks the single-site change pattern without requiring the full after-scene graph to be correct. Baseline evaluations on ground-truth-mask backbones, learned-slot models, SAM 2 + frozen-ViT models, and one mask-feature hybrid indicate that CoGenT-OOD-core degradation can persist under ground-truth instance masks, that mask source accounts for part but not all of native performance, and that locality or stability alone can overstate semantic faithfulness. Code is available at https://github.com/torux-bughunter/EditCLEVR.

Anuraag Gadehothur Karnam, Tarunesh Sathish

Lebanon Trail High School · Walnut Grove High School

Counterfactual Evaluation Object-Centric Representation Learning Compositional Generalization

Jul 15, 2026cs.CL

Constraint-Aware Counterfactual Editing for Aspect-Based Sentiment Analysis

Aspect-Based Sentiment Analysis (ABSA) requires models to identify sentiment toward specific aspects rather than relying on the global polarity of a sentence. This makes counterfactual evaluation especially challenging: a valid counterfactual should flip the sentiment of one target aspect while preserving the sentiment of all non-target aspects, semantic meaning, fluency, and factual consistency. Existing counterfactual generation methods often focus on sentence-level label flipping and may produce edits that are fluent but aspect-invalid, semantically drifting, or contradictory. To address this limitation, we propose CAVE-ABSA, a Constraint-Aware Validated Editing framework for generating and validating aspect-level counterfactuals. CAVE-ABSA localizes the opinion span associated with the target aspect, performs controlled counterfactual rewriting, refines candidates through a repair module, and filters them using aspect-level verification, semantic similarity, AMR-guided structural preservation, edit minimality, fluency, and contradiction detection. The framework is designed to construct validated counterfactual ABSA datasets for robustness evaluation and data augmentation. By explicitly separating generation from validation, CAVE-ABSA provides a principled approach for producing meaningful aspect-local counterfactuals and for testing whether ABSA models truly rely on aspect-grounded sentiment reasoning.

S M Rafiuddin, Vamsi Krishna Pavuluri, Atriya Sen

Department of Computer Science, Oklahoma State University, Stillwater, Oklahoma, USA

Counterfactual Evaluation Counterfactual Explanations Counterfactual Data Augmentation Aspect-Based Sentiment Analysis

Jul 4, 2026cs.CL

NormWorlds-CF: Solver-Verified Counterfactual Normative Reasoning with Metamorphic-Relation GRPO

Language models can reach the right normative verdict for the wrong reason. We introduce NormWorlds-CF, a solver-verified environment for counterfactual normative reasoning in executable rule worlds. Its deterministic solver produces final answers, proof and falsification certificates, argument statuses, support sets, and paired-world change labels, enabling supervision and evaluation without LLM judges. The benchmark contains staged SFT diagnostics and a compact paired-world task with 270 root families and 1080 canonical-to-variant pairs. The SFT diagnostics show that final-answer supervision is an unsafe proxy: answer-only SFT reaches perfect accuracy on answer tasks but scores zero on falsification, while proof-plus-falsification training with targeted replay reaches strong all-task accuracy. For the structured-change task, we introduce metamorphic-relation GRPO (MR-GRPO), a class-conditioned reward for GRPO that gives partial credit for relation families and solver-visible change fields. In matched 1.7B continuation experiments, MR-GRPO improves held-out relation accuracy and relation-family correctness, and reduces wrong-family error, compared to sparse and answer-only GRPO. In Qwen3-4B three-seed validation, answer-only reward improves answer-change fields but weakens relation-family structure, sparse reward preserves coarse relation labels best, and MR-GRPO delivers the strongest balanced performance across answer-change, support-change, status-change, and soft root-level metamorphic-relation metrics. These results show that verified counterfactual structure can shape post-training beyond final answers, while exact full change-record generation, invariant subtype recognition, and out-of-distribution (OOD) transfer remain open problems.

Xinqi Zhang

Tsinghua University

Counterfactual Evaluation Moral Reasoning in Language Models RL for Language Model Reasoning Counterfactual Reasoning in Language Models Group Relative Policy Optimization Counterfactual Reasoning

Jul 4, 2026cs.CV

Do Medical Vision Language Models Actually See? A Counterfactual Grounding Framework and Hard-Negative Contrastive Training for Visually-Reliant Medical VLMs

Large vision language models (VLMs) report strong accuracy on medical question-answering, yet it remains unclear whether they reason from visual evidence or exploit textual shortcuts. We introduce a counterfactual evaluation framework that decouples visual and textual contributions by substituting input images with controlled surrogates blank, pixel-shuffled, image-absent, and CLIP-retrieved hard negatives and derive a suite of grounding metrics including the Visual Reliance Score (VRS) and Visual Hallucination Rate (VHR). We further introduce CORAL (COntrastive Retrieval-Augmented Learning), a 7B-parameter LoRA fine-tune of Qwen2.5-VL-7B trained with a Contrastive Grounding Objective (CGO) that penalises answer invariance under hard-negative image swaps. On a paired controlled evaluation across four closed-form medical VQA benchmarks (PathVQA, PMC-VQA, SLAKE, VQA-RAD; n=400 total), CORAL improves macro accuracy by +6.7 pp (P(Delta>0)=0.988) and reduces VHR by 8.0 pp (P<0.001) over the matched Qwen2.5-VL-7B base; neither MedVLThinker RL variant achieves a significant gain on either metric. Cross-domain diagnostics further reveal that image substitution costs only <=6.5 pp on medical benchmarks versus 48-61 pp on general-domain tasks, situating the grounding gap that CGO targets. We discuss evaluation limitations openly including train/eval benchmark overlap and underpowered secondary metrics and release our framework, training code, and model weights to support reproducible grounding audits of medical VLMs.

Anas Zafar, Leema Krishna Murali, Siddhant Bharadwaj +2

The University of Texas MD Anderson Cancer Center · Eisai Inc. · Cohere Labs Community +1

VLM Evaluation Counterfactual Evaluation Contrastive Learning Medical VQA Vision-Language Grounding Medical VLMs

Jun 29, 2026cs.AI

A causal modeling perspective on decision theory

Decision theory provides a formal framework for how agents should make choices under uncertainty, drawing on ideas from philosophy, probability, and causality. Despite significant progress, the field still lacks a unified modeling language, and key concepts - such as the distinction between subjective and objective elements, or what it means for a decision theory to perform well - are often left implicit. This can make it difficult to evaluate and compare competing theories, particularly in controversial cases. In this paper, we address these issues by introducing a formal framework for decision theory based on nonparametric structural equation models (NPSEMs), a well-established tool in causal inference. NPSEMs provide a unified foundation for representing agents, counterfactuals, and causal relationships, allowing for unambiguous definitions of EDT and CDT. Building on this foundation, we propose a novel decision theory - personal decision theory - which instructs agents to maximize a subjective model of their own counterfactual utility. We introduce a formal performance metric based on hypothetical interventions that enforce a given decision theory across a population - such as might be achieved through education or policy -- and show that, under certain assumptions, personal decision theory is optimal with respect to this metric. Throughout, we use the smoking lesion problem as a running example and conclude with a formal analysis of Newcomb's problem. Our aim is to provide decision theory with a clearer modeling language and firmer evaluative ground, thereby enabling more rigorous comparisons and facilitating conceptual progress in the field.

Arvid Sjölander

Karolinska Institutet

Counterfactual Evaluation

Jun 16, 2026physics.soc-ph

Public transit gains and spatially uneven travel demand changes after NYC congestion pricing

New York City implemented the nation's first cordon-based congestion pricing program in January 2025, providing an opportunity to evaluate how system-wide urban mobility responds to large-scale pricing interventions. Because such policies generate spillovers across modes and locations, credible control groups are difficult to construct. We address this challenge using time series foundation models to generate probabilistic counterfactual demand forecasts with calibrated uncertainty. Applying this framework to bus, subway, and aggregate trip volume data, we find that post-policy bus and subway ridership increased significantly relative to expected no-policy demand, while overall travel demand decreased modestly. The effects are spatially heterogeneous: while reductions in overall travel demand are concentrated within the Congestion Relief Zone, transit gains extend beyond Manhattan's core. Socio-demographic analyses further reveal uneven adaptation across neighborhoods, highlighting spatial equity implications. Our framework provides a scalable approach for the uncertainty-aware evaluation of system-wide urban interventions when clean control groups are unavailable.

Donghang Li, Dingyi Zhuang, Yunlin Li +5

Department of Civil and Environmental Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA · Department of Urban Studies and Planning, Massachusetts Institute of Technology, Cambridge, MA, USA · Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA +4

Counterfactual Evaluation Causal Effect Estimation Dynamic Pricing

Jun 14, 2026cs.CV

Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations

Multimodal models can name the action units (AUs) behind a facial emotion, but their AU->emotion rationales are typically plausible rather than faithful: nothing forces the AUs a model invokes to be the AUs that actually drive its prediction. We cast AU->emotion reasoning as a counterfactual-consistency problem between the rationale, the label, and a structural AU->emotion causal graph G, and propose FACR, which grounds the reasoner in an independently induced, polarity-aware G and trains a counterfactual-faithfulness objective: a do-intervention on an AU that G marks causal for a class must move the prediction, while one it marks irrelevant must leave it unchanged. Faithfulness is thereby both trainable and measurable through a matching interventional metric, which we evaluate against a known causal structure, the PSPI pain-AU composition, as no existing affective-reasoning benchmark allows. We are explicit that this metric tests fidelity to the supplied structure rather than its rediscovery: it asks whether the trained reasoner invokes the AUs the structure marks causal, on held-out subjects and a second dataset. Under subject-independent evaluation on UNBC-PAIN, the objective raises the agreement between the invoked AUs and the PSPI composition from a no-objective baseline of 0.08 to 0.57, at a small detection cost; an unfaithfulness control attributes the gain to the objective. On a cross-dataset emotion transfer, the objective likewise raises fidelity to G on a seven-class task (0.50 to 0.84). Finally, we attach a language verbalizer and extend the audit to the generated text: biasing each action unit's emission by its latent activation makes the rationale faithful by construction, so that ablating an AU removes it from the explanation, a property that transfers to a second language-model backbone, whereas a freely generated rationale is unfaithful.

Van Thong Huynh, Hong Hai Nguyen, Thuy Pham +2

Faculty of CSE, Ho Chi Minh City University of Technology (HCMUT), VNUHCM, Vietnam · Dept. of AI, FPT University, Vietnam · Faculty of DSAI, College of Technology, National Economic University, Vietnam +1

Counterfactual Evaluation Counterfactual Explanations Causal Attribution Facial Expression Recognition Causal Reasoning Counterfactual Learning

Jun 14, 2026cs.LG

Re-feeding Is Not Replaying: Measuring Replay Noise in Counterfactual Token-Credit Estimation

Per-token counterfactual credit estimation asks which token in a language-model rollout caused the final answer to be right or wrong: cut the transcript at a pivot, substitute an alternative token, replay continuations, and compare outcomes. Published methods re-feed the transcript prefix as a fresh prompt, assuming this reproduces the state the model passed through during generation. We measure what that assumption costs on a stock inference engine, with a three-pass design: continuations resumed from the verified decode-time KV state, an identical second exact pass (a replica noise floor), and a re-feed pass. Across six configurations and three models (including a GRPO-trained checkpoint), at low-margin decision tokens, re-feeding changes the credit estimate at rates 14-28 percentage points above the replica floor (7-21pp under a treatment-independent conditioning; problem-clustered t = 2.9-6.4). Most changes are zero-boundary crossings of the quantized estimator rather than polarity reversals, and the perturbation is consistent with mean-zero, so averaged quantities are largely safe; but selection is not: a critical-token set chosen by thresholding

|\hat{A}_t|

under re-feed overlaps the exact-resume selection at Jaccard 0.34-0.90, versus a 0.63-0.96 replica ceiling. A causal confirmation closes the loop: under vLLM's batch-invariant kernels all three passes are identical on every measured channel, with both disagreement rates exactly zero. Replica passes themselves disagree on 9-23% of eligible estimates: single-sample credit measurements at decision tokens are unreliable under any replay. Settings were fixed in advance; exact-pass cache hits in the second campaign are instrumented (100% hit rate, 3,434 pivots); total compute was under 10 USD. We recommend that counterfactual credit studies resume decoder state or use batch-invariant kernels, and report a replica floor.

Nils Matteson

Northeastern University

Counterfactual Evaluation Token-Level Credit Assignment Counterfactual Reasoning in Language Models LLM Reliability Causal Interventions in Language Models Counterfactual Credit Assignment

Jun 9, 2026cs.AI

Monte Carlo Pass Search: Using Trajectory Generation for 3D Counterfactual Pass Evaluation in Football

We recast pass evaluation in football (soccer) as a Monte Carlo Tree Search (MCTS)-like evaluation problem whose components mostly exist in the literature under different names: a value model (possession value), a world model (multi-agent trajectories with ball interactions), and a policy over counterfactual actions (sampling pass variants with noise). Building on the first public high-fidelity tracking dataset with 3D ball trajectories from the Bundesliga, we introduce Monte Carlo Pass Search (MCPS), which infers kick parameters for each observed pass, samples execution variants and option variants, rolls each candidate forward with a ball-conditioned world model until the next ball interaction, and scores outcomes with a learned value model to obtain a distribution over gained value. This distribution enables distribution-aware attribution with two complementary execution-surplus scores used for analysis and ranking: mean-based and percentile-based scores. To make the world model sample-efficient under limited public data, we adapt a discrete-token, autoregressive trajectory generator from autonomous driving (SMART) and show it yields strong best-of-20 forecasting accuracy compared to baselines, while supporting fully hypothetical rollouts for downstream evaluation. We have released model checkpoints and code.

Andrew Kang, Priya Narasimhan

Carnegie Mellon University · Pittsburgh, USA

Counterfactual Evaluation Multi-Agent Trajectory Prediction Sports Video Analysis Monte Carlo Tree Search

Jun 6, 2026cs.LG

Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures

When an LLM agent fails -- issues a refund it should not have, calls the wrong tool, leaks data -- existing tooling answers what happened (observability) or whether it passed (evaluation), but not which step caused the failure. The obvious heuristics are wrong: the step that executes the harmful action is usually not the step that decided on it, and LLM-judge attribution is correlational and unreliable (state-of-the-art step-level accuracy on the Who&When benchmark is about 14%). We present Causal Agent Replay (CAR), which answers the question by intervention: it models an agent run as a structural causal model, applies a do-operation to a step, and re-executes the trajectory forward under the same stochastic policy, measuring the shift in the outcome distribution. We define an intervention algebra over agent steps, a single-step contrastive estimator whose point-of-commitment rule resolves a confound specific to stochastic run-forward, and a budget-bounded Monte-Carlo Shapley estimator that splits credit across interacting steps. Every effect is reported with confidence intervals. We validate against synthetic structural causal models with planted ground truth: the contrastive estimator recovers the pivotal step, and Shapley recovers a two-step interaction (0.44, 0.45, ~0; efficiency sum 0.909 versus the analytic 0.91). CAR is open source and runs on hosted or free local models.

Jaineet Shah

Agent Failure Analysis AI Agent Reliability Counterfactual Evaluation Causal Attribution Causal Inference Counterfactual Credit Assignment

Jun 6, 2026q-fin.TR

Post-Rejection Follow-up Sampling: A Methodology for Counterfactual Outcome Measurement in Algorithmic DEX Trading

Algorithmic trading systems on decentralised exchanges (DEXs) reject most candidate tokens they evaluate. The counterfactual outcome of rejected candidates (what would have happened had the system entered) is rarely measured. This paper introduces Post-Rejection Follow-up Sampling (PRFS). A separate tracking subsystem samples each rejected token's price and liquidity at a configurable cadence, over a horizon of up to twenty-four hours. PRFS produces the data needed to evaluate filter precision against actual market outcomes of rejected candidates, not against synthetic backtest reconstructions. The methodology, data architecture, and deposit format are described in Section III. The companion dataset contains 67,000 forward-outcome observation rows across 2,997 rejection events spanning 457 unique mints, collected over a continuous eight-day window (2026-04-10 to 2026-04-19, UTC). Approximately 55 percent of rejection events receive at least one forward observation; coverage at the mint level is complete. The principal binding constraint on downstream classification is per-event horizon density, not event-level coverage. PRFS is dataset-independent. It generalises to any algorithmic decision system in which rejections substantially outnumber executions.

Arati Uday Kamat

Independent Researcher

Counterfactual Evaluation Decentralized Finance Finance Selective Labels Algorithmic Trading

Jun 4, 2026cs.CL

Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions

Large language models are increasingly used to simulate social media users and infer how individuals may respond to online discussions. However, it remains unclear whether these simulations reflect precise user-specific beliefs or whether they are highly sensitive to semantically independent changes in conversational contexts. In this work, we study counterfactual context revision as a framework for auditing LLM-based stance simulation. Given an original online conversation, we first infer a target user's stance toward a specific topic. We then apply controlled revision strategies to the conversational context and simulate the user's stance again under the revised context. We compare text-only revision strategies with a multimodal one that incorporates meme-based context and evaluate two main effectiveness metrics, i.e., average directional stance shift and stance transition rate. The results reveal effective and robust stance transitions in both text-only and multimodal strategies across different polarization-preference mechanisms. Our study contributes an evaluation framework for understanding the context sensitivity of LLM-based stance simulation (https://github.com/STARResearchLab/StanceShift). More broadly, it highlights both the promise and risk of using LLMs as proxies for social media users in social simulation.

Xinnong Zhang, Wanting Shan, Hanjia Lyu +2

1Fudan University · 3Shanghai Innovation Institute · University of Rochester

Counterfactual Evaluation LLM Auditing Large Language Model-Based Social Simulation Language Model Robustness

Jun 2, 2026cs.LG

A Geometric View of Counterfactual Behavior: Interaction of Boundary Proximity and Local Support

Counterfactual explanations seek small, semantically meaningful changes to an input that alter a model's prediction, and are widely used to interpret and audit machine learning systems. In modern vision, language, and multimodal systems, pretrained encoders map inputs to representation spaces, and downstream classifier heads impose decision boundaries within those spaces. As a result, the feasibility and distance of nearby counterfactuals depend on boundary placement relative to the data. Yet models with similar predictive performance can differ substantially in whether such changes are achievable and how far representations must move. This work examines this variation using a standardized local search probe across several pretrained encoders and linear classifier heads. Results show that despite similar predictive performance, models differ substantially in their counterfactual behavior. Under fixed representations, varying only the classifier head alters counterfactual outcomes while leaving predictive performance largely unchanged. This variation is explained by the interaction of decision-boundary proximity and local data support, which jointly determine whether prediction changes are both feasible and lie in regions supported by the data, and can also improve counterfactual search within fixed models. Together, these findings identify counterfactual behavior as a distinct dimension beyond predictive performance and show that it can be altered without changing accuracy, with implications for model selection, robustness, and the reliability of counterfactual methods.

Ioanna Gemou, Matteo Gamba, Randall Balestriero +1

Brown University

Counterfactual Evaluation Counterfactual Explanations

May 28, 2026cs.LG

Counterfactual Evaluation Reveals Hidden Capability Profiles in Clinical LLMs and Agents

Two clinical AI systems can score nearly identically on coverage-based rubrics yet behave radically differently when their patient inputs change: one updates its recommendations to match the new clinical signal, while the other produces the same output regardless. We introduce the Causal Sensitivity Score (CSS), a pre-registered interventional metric that mutates oncology tumor-board cases along five clinically meaningful dimensions - biomarker flips, prior-treatment failures, biomarker removals, surgery-status changes, and stage perturbations - and scores whether each model updates its recommendations in the pre-registered correct direction using a {0, 0.5, 1.0} scale. Benchmarked against the Consensus Match Score (CMS), a coverage-based weighted recall metric, six frontier models from three labs evaluated in single-shot inference across 224 cases rank in nearly opposite orders: all six models change rank, the CMS-worst model becomes CSS-best, and one upper-mid CMS model ranks last on CSS. We further surface a universal safety blind spot: every frontier model fails on surgery-status interventions (at most 17.2% CSS on Family D), a finding CMS does not expose. The metric also transfers to tool-using agents: in a ReAct-style experiment, tool use improves CSS for five of six models (+2.5 to +20.3 percentage points), yet the lowest-CSS model retrieves the same chart sections and still fails to update its recommendations - revealing a structural responsiveness deficit visible only under counterfactual evaluation. Cross-judge replication and three-rater medical-professional validation confirm the aggregate findings. Interventional pre-registered metrics like CSS complement coverage-based evaluation for clinical AI agents: they capture responsiveness that coverage metrics miss and offer a candidate dense reward signal for future agentic RL systems.

Matt Turk

Protege Data Lab New York City, USA

Counterfactual Evaluation Healthcare Clinical Decision Support LLM Agent Evaluation Clinical Language Model Evaluation

May 28, 2026cs.CV

DMC-CF: Dynamic Multimodal CounterFactual QA benchmark for Causal Reasoning

With the rapid advancement of multimodal large language models (MLLMs), models have demonstrated increasingly powerful multimodal capabilities. However, whether MLLMs trained through statistical learning can truly understand the causal relationships underlying the real world remains a key research question. In recent years, numerous multimodal causal reasoning datasets have been proposed. Nevertheless, these datasets are either limited in scale or constructed from synthetic images and videos, cartoon-based content, or other non-realistic multimodal sources. To address these limitations, we collect real-world videos and construct DMC-CF-Static, a large-scale benchmark for multimodal causal counterfactual reasoning. Furthermore, to mitigate issues such as data contamination in traditional static evaluation, we represent causal events using causal graphs and propose the Dynamic Graph Intervention (DGI) framework to build the dynamic evaluation benchmark DMC-CF-Dynamic from DMC-CF-Static. Experimental results on the overall DMC-CF, which includes both static and dynamic evaluation benchmarks, demonstrate that the multimodal causal reasoning capabilities of current multimodal large language models in real-world scenarios still require substantial improvement.

Junzhe Zhang, Huixuan Zhang, Guirong Wang +5

Wangxuan Institute of Computer Technology, Peking University · Alibaba Group

Counterfactual Evaluation Counterfactual Reasoning in Language Models Multimodal Large Language Models Multimodal QA Multimodal Reasoning Causal Reasoning in Videos+1

May 27, 2026cs.AI

When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it, we introduce context-flip evaluation, testing 12 models across a safety benchmark (PacifAIst) and two commonsense controls using paired variants where the nominally safe action produces harm. Three findings emerge. First, brittle safety is safety-specific: all 12 models exhibit a safety-commonsense gap (mean +17.4 pp). Baseline accuracy fails to predict brittleness: among models above 90% baseline accuracy, brittleness rates range from 13.7% to 90.0%. Second, failures stem from policy override rather than miscomprehension: despite acknowledging the context change in every case, models persist via three distinct mechanisms that vary by update type and model family. Third, on a hand-audited probe of catastrophic consequence-flip scenarios, standard action-level guardrails catch none, while a state-aware validator catches all without false alarms on correct interventions. This indicates that action-level content moderation is systematically blind to consequence-flips, motivating state-aware architectural alternatives. We release our protocol, perturbed benchmarks, and deployment probe.

Dasol Choi, Alex Kwon

AIM Intelligence · Independent Researcher

LLM Safety Benchmarks Counterfactual Evaluation Language Model Safety Evaluation LLM Guardrails AI Agent Safety Benchmarks

May 26, 2026q-fin.RM

Foundations of a Time-Consistent Counterfactual Actuarial Runtime for Autonomous AI Agents

We propose a foundational runtime actuarial layer for autonomous AI agents in which every side-effect-bearing action carries a time-consistent, counterfactual risk toll computed against a contractually fixed safe default, inside an explicit underwriting boundary. The framework treats per-action insurance as the primary unit of analysis and replaces post-hoc annual liability cover with a pre-action transaction layer. The paper establishes four structural results: (i) a well-defined counterfactual toll under a chosen safe-default mapping and continuation policy, with explicit non-uniqueness; (ii) a no-splitting property within an underwriting boundary that telescopes path-decomposed actions into a boundary potential, with a corollary tying gaming-resistance to boundary design; (iii) an irreversible-authority premium, split into a strictly positive action-level component and an if-and-only-if characterisation of the set-level robust capital increase; and (iv) a conservative runtime gating theorem that translates high-probability toll envelopes into an executed-action budget guarantee. The result is the mathematical base layer for a broader program: an empirical companion instantiates the runtime through an Actuarial Action Interface and authority-frontier experiments; a mechanism-design companion studies strategic operator incentives and cross-boundary aggregation; and a dynamic-underwriting companion studies experience rating and audit-replay calibration. The present paper states the primitive contract, the toll identity, the within-boundary no-arbitrage result, and the budget guarantee on which those later layers depend.

Hao-Hsuan Chen

Department of Risk Management and Insurance National Chengchi University

Counterfactual Evaluation AI Risk Management AI Agent Safety Runtime Assurance

May 22, 2026cs.CL

Metadata Predictability Is Not Evidence Dependence: An Intervention-Based Audit for Weak-Label Benchmarks

We study a protocol-level test for weak-label benchmarks: whether benchmark outputs change when the provided evidence is intervened on. Metadata-only shortcut checks answer a different question, namely whether outputs are predictable from metadata priors. We therefore combine a metadata statistic, the Metadata Prior Dominance Score (MPDS), with an evidence-intervention statistic, ΔEvi, measuring sensitivity to evidence identity under cross-item shuffling. Synthetic HotpotQA gives a constructed counterexample to metadata-only screening: MPDS is only moderate (0.643), yet ΔEvi is zero. Stronger-reader reruns show why calibration belongs in the test procedure: SNLI shows a calibration reversal, reconstructed HotpotQA occupies a question-dominant warning region, and FEVER is a strongly evidence-sensitive positive control across four transformers. The practical lesson is simple: benchmark audits should report metadata-only screening, evidence intervention, and reader-strength calibration together.

Kan Shao

Jinglue Technology Development (Nanjing) Co., Ltd., Nanjing, China

Counterfactual Evaluation Benchmark Auditing Benchmark Design Benchmark Validity

May 22, 2026cs.CV

CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models

Video prediction is increasingly viewed as a path toward generalizable world models, yet it remains unclear whether these systems learn underlying causal structure or merely exploit superficial visual correlations for future prediction. We introduce CRONOS, an intervention-based benchmark designed to evaluate counterfactual physical consistency: whether a model's predictions of physical events respond appropriately to controlled changes in the visual input, such as variations of scene context, viewpoint, object appearance, and object category. Built in a photorealistic Unreal Engine environment, CRONOS enables controlled, high-fidelity generation of videos across diverse scenes and dynamics. In contrast to previous benchmarks, CRONOS systematically intervenes on four key factors - viewpoint, scene, object category, and object appearance - while keeping the underlying physical event type, such as a collision, occlusion, or fall, fixed. Our evaluation of recent open-source video generators reveals substantial failures in counterfactual physical consistency: prediction quality for the same physical event type is affected by appearance, environment, and, particularly by viewpoint changes. CRONOS provides a controlled and reproducible testbed for diagnosing how the quality of generated videos changes for different interventions, establishing a concrete target for developing models that perform consistently across changes of multiple conditions. The dataset and code are available at our project page.

León Begiristain, Olaf Dünkel, Adam Kortylewski

University of Freiburg · Freiburg im Breisgau, Germany · Max Planck Institute for Informatics +3

Counterfactual Evaluation Physical Consistency in Video Generation Video Prediction Causal Reasoning in Videos Video Generation Evaluation

May 21, 2026cs.CV

Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning

Video large language models (Video LLMs) can achieve strong video-QA accuracy without reliably tracking spatiotemporal dynamics. A model may answer a motion question from static cues, for example, and give the same prediction even after the underlying motion is reversed. Correctness-based reinforcement learning does not directly address this problem because it rewards the final answer without requiring the policy to respond to task-relevant video dynamics. We propose Counterfactual Relational Policy Optimization (CRPO), which explicitly trains Video LLMs to respond to controlled changes in the visual input. For each training example, CRPO constructs a counterfactual video, such as a horizontally flipped or temporally reversed version of the original, and jointly optimizes rollouts from both videos under a shared policy. Factual supervision anchors what the model should answer, while counterfactual supervision constrains when that answer should change: predictions should change when an intervention alters task-relevant dynamics and remain stable when the queried property is preserved. This coupling provides a direct behavioral learning signal without requiring ground-truth labels for transformed videos or annotated spatiotemporal reasoning traces, while discouraging indiscriminate answer changes. To evaluate this property, we introduce DyBench, a paired counterfactual benchmark with 3{,}014 videos and a strict pair-accuracy metric. Across paired spatiotemporal evaluations and standard video benchmarks, CRPO improves sensitivity to motion and temporal changes while improving performance on general video understanding. The gains also extend to segment reordering, a transformation never used during training, suggesting that CRPO learns sensitivity to video dynamics beyond the training interventions. The project website can be found at https://ddz16.github.io/crpo.github.io/ .

Dazhao Du, Jian Liu, Jialong Qin +7

Hong Kong University of Science and Technology · Tencent

Counterfactual Evaluation Video-Language Models Counterfactual Learning RL for VLMs Temporal Video Understanding

May 18, 2026cs.LG

Counterfactual Likelihood Tests for Indirect Influence in Private Reasoning Channels

Reasoning systems increasingly separate intermediate computation into private and public channels, creating evaluation cases that look similar in transcripts: independent co-derivation, direct access to private content, and indirect influence through public communication. This paper presents a counterfactual likelihood test for measuring influence between private reasoning channels. The method replaces an upstream private block with a length-matched donor block, holds the public token sequence and downstream target fixed, and measures the downstream target's negative-log-likelihood shift. On a 7B role-channel reasoning model used for validation, textual probes are unreliable: raw n-gram overlap overstates leakage, corrected overlap remains noisy, and canary reproduction reports no discrimination. Counterfactual likelihood separates unmasked and masked conditions, while length matching controls a RoPE positional confound. In the hardened masked validation, reverse B-to-A influence is near zero, while A-to-B influence persists through public-speech hidden states. A multi-checkpoint validation across three checkpoints, five seeds, and 13,734 valid directional contrasts replicates this asymmetry. A graph-separation control that blocks private-to-public carrier edges produces bit-identical natural and counterfactual scores across all 13,734 control evaluations, identifying the tested public-channel pathway as the complete carrier of the measured counterfactual signal under the implemented role-visibility mask. The results show that private-channel evaluation should report direct and indirect influence separately, and that counterfactual likelihood probes provide a practical default for measuring these boundaries.

Alexander Boesgaard Lorup

Openhagen

Counterfactual Evaluation LLM Interpretability Privacy Leakage in Language Models Causal Interventions in Language Models

May 16, 2026cs.LG

When Bits Break Recourse: Counterfactual-Faithful Quantization

Quantization can preserve predictive accuracy under low-bit deployment while silently breaking algorithmic recourse: an actionable change that flips a decision before quantization may fail after quantization, or become substantially more costly. We formalize counterfactual sensitivity under quantization through validity, cost, and direction stability, and introduce two metrics: Validity Drop (VD) and Counterfactual Recourse Gap (CRG) that reveal recourse failures invisible to accuracy. We propose Counterfactual-Faithful Quantization (CFQ), which trains quantizer parameters and mixed-precision bit allocation to preserve counterfactual behavior by enforcing the target outcome at teacher recourse points under a global bit budget. A margin-based analysis gives a sufficient condition for recourse transfer under bounded quantization perturbations. Experiments on Adult, German Credit, and COMPAS show that accuracy-matched baselines can significantly degrade recourse stability, while CFQ maintains accuracy and substantially improves VD and CRG across bit budgets.

Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui +1

Mohammed First University

Mixed-Precision Quantization Counterfactual Evaluation Quantization-Aware Training Low-Bit Quantization Algorithmic Recourse

May 14, 2026cs.LG

What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions

Time series forecasting has become increasingly critical in real-world scenarios, where future sequences are influenced not only by historical patterns but also by forthcoming events. In this context, forecasting must dynamically adapt to complex and stochastic future conditions, which introduces fundamental challenges in both forecasting and evaluation. Traditional methods typically rely on historical data or factual future conditions, while overlooking counterfactual scenarios. Furthermore, many existing approaches are restricted to simple structured conditions, limiting their ability to generalize to the real-world complexities. To address these gaps, we introduce the task of counterfactual time series forecasting with textual conditions, enabling more flexible and condition-aware forecasting. We propose a comprehensive evaluation framework that encompasses both factual and counterfactual settings, even in the absence of ground truth time series. Additionally, we present a novel text-attribution mechanism that distinguishes mutable from immutable factors, thereby improving forecast accuracy under sophisticated and stochastic textual conditions. The project page is at https://seqml.github.io/TADiff/

Shuqi Gu, Yongxiang Zhao, Baoyu Jing +1

School of Information Science and Technology, ShanghaiTech University, Shanghai, China · University of Illinois at Urbana-Champaign, Illinois, United States.

Counterfactual Evaluation Time Series Forecasting Counterfactual Prediction

May 14, 2026cs.AI

Heuristic Pathologies and Further Variance Reduction via Uncertainty Propagation in the AIVAT Family of Techniques

How should an agent's performance in a multiagent environment be evaluated when there is a limited sample size or a high cost of running a trial? The AIVAT family of variance reduction techniques was proposed to address this challenge by introducing unbiased low-variance estimators of agents' expected payoffs. An important component of AIVAT is a heuristic value function that discriminates between potentially low- and high-value counterfactual histories. A notable gap in the literature is that there is little to no constraint or guideline on how the heuristic value function should be chosen or how uncertainty in its output should be handled. In our first contribution, we parameterize the heuristic value function to highlight AIVAT's potential vulnerabilities: a) the sample variance can be set pathologically low by directly applying gradient descent on the sample variance, and b) one can p-hack to draw a desired statistical conclusion via gradient descent/ascent on the test statistic. The main takeaway is that the heuristic value function should be fixed prior to observing the evaluation data! In our second contribution, we show how the heuristic uncertainty can be propagated to quantify the uncertainty of AIVAT estimates. It is then possible to further reduce the variance using inverse-variance weighted averaging, but AIVAT's unbiasedness guarantee may have to be sacrificed. In our experiments, we use a dataset of 10,000 poker hands to demonstrate our heuristic pathology and uncertainty results, with the latter yielding a 43.0% reduction in the number of samples (poker hands) needed to draw statistical conclusions.

Juho Kim, Tuomas Sandholm

Computer Science Department Carnegie Mellon University

Counterfactual Evaluation Uncertainty Quantification Agent Evaluation Uncertainty Propagation Variance Reduction

May 11, 2026cs.LG

A Proof-of-Concept Simulation-Driven Digital Twin Framework for Decision-Aware Diabetes Modeling

This paper presents a proof-of-concept digital twin framework for simulation-driven diabetes modeling using benchmark clinical data, synthetic temporal augmentation, and illustrative continuous glucose monitoring (CGM) analysis. Unlike traditional predictive models, the framework focuses on generating interpretable simulated trajectories rather than clinically validated outcomes. Evaluation is conducted using a public dataset combined with controlled synthetic scenarios to illustrate temporal behavior and intervention effects. Results illustrate the feasibility of integrating prediction with counterfactual simulation for decision-aware analysis. This work does not claim clinical readiness but provides a foundation for future research on simulation-driven digital twin systems in healthcare.

Zarrin Monirzadeh

Portland, OR, USA

Counterfactual Evaluation Digital Twins

May 11, 2026cs.LG

Real vs. Semi-Simulated: Rethinking Evaluation for Treatment Effect Estimation

Estimating heterogeneous treatment effects with machine learning has attracted substantial attention in both academic research and industrial practice. However, the two communities often evaluate models under markedly different conditions. Methodological work typically relies on semi-simulated benchmarks and metrics that require counterfactual outcomes, whereas real-world applications rely on observable metrics based on ranking or test outcomes. Despite the well-known gap between methodological progress and practical deployment, the relationship between these evaluation regimes has not been examined systematically. We conduct a large-scale empirical study of treatment effect evaluation across standard semi-simulated benchmark families and real-world datasets. Our benchmark covers meta-learners paired with multiple base learners, as well as specialized causal machine learning models. We evaluate these methods using observable metrics common in application-oriented literature, alongside counterfactual metrics commonly used in methods papers. Our results reveal two complementary gaps. First, counterfactual metrics do not reliably recover the estimators preferred by observable metrics, even on the same semi-simulated benchmarks. Second, rankings obtained on semi-simulated benchmarks do not transfer to real datasets. We further find that simple meta-learners with strong base models are consistently competitive, in contrast to specialized causal models. Overall, our findings suggest that progress in treatment effect estimation research should not be assessed solely through counterfactual metrics and semi-simulated benchmarks, but it would benefit from incorporating observable metrics and real-data validation.

George Panagopoulos

Department of Computer Science University of Luxembourg 2 Av. de l’Universite, 4365 Belval Esch-sur-Alzette

Counterfactual Evaluation Causal Effect Estimation Individualized Treatment Effect Estimation Synthetic Data Evaluation

May 1, 2026cs.CL

Compared to What? Baselines and Metrics for Counterfactual Prompting

Counterfactual prompting (i.e., perturbing a single factor and measuring output change) is widely used to evaluate things like LLM bias and CoT faithfulness. But in this work we argue that observed effects cannot be attributed to the targeted factor without accounting for baseline ``meaning-preserving'' modifications to text that establish general model sensitivity. This is because every counterfactual edit is a compound treatment that bundles the variable of interest with incidental surface-form variation; this violates treatment variation irrelevance. We observe prediction flip rates on MedQA of 14.9% when we surgically change patient gender. However, this is statistically indistinguishable from the flip rates induced by simply paraphrasing inputs (14.1%). In this case, it would therefore be unwarranted to conclude that the LLM is especially sensitive to patient gender. To account for this and robustly measure the effects of targeted interventions, we propose a framework in which we compare (via statistical testing) differences observed under target interventions to those induced by paraphrasing inputs. We then use this framework to revisit a analysis done on the MedPerturb dataset, which reported evidence of model sensitivity to patient demographics and stylistic cues. We find that these effects largely dissipate when we account for general model sensitivity, with only 5 of 120 tests reaching statistical significance. Applying the same framework to occupational biography classification, we detect clearly significant directional gender bias, showing that the framework identifies real directional effects even when they are small. We evaluate a range of metrics -- aggregate, per-sample distributional, and regression -- and find that per-sample metrics are dramatically more powerful than aggregate metrics and regression powerfully and uniquely characterizes effect direction and magnitude.

Zihao Yang, Mosh Levy, Yoav Goldberg +1

Northeastern University · Bar-Ilan University · Allen Institute for AI

Counterfactual Evaluation Causal Interventions in Language Models

Apr 28, 2026econ.EM

Auditing Marketing Budget Allocation with Hindsight Regret

Organizations routinely make strategic budget allocations under operational constraints, but often lack a principled way to assess whether realized allocations were close to the best feasible choices in hindsight. We present a retrospective auditing framework based on hindsight regret, defined as the opportunity cost of the realized allocation relative to a constraint-faithful benchmark under the same budget and stability guardrails. The framework estimates regime-specific spend--response functions from historical logs, computes feasible hindsight allocations via constrained optimization, and propagates uncertainty through Monte Carlo evaluation to produce regret distributions, expected lift, and probability-of-improvement summaries. This separates allocation inefficiency from uncertainty in the estimated response surfaces. Experiments on real marketing allocation logs show that the framework yields interpretable post-hoc diagnostics and reveals a practical trade-off between allocation flexibility and detectability: moderate feasible reallocations often capture most measurable gain, while larger shifts move into weak-support regions with higher uncertainty. The result is a practical method for auditing historical budget decisions when online experimentation is costly or infeasible.

Nilavra Pathak, Olivier Jeunen, Eric Lambert

Expedia Group · New York, USA · aampe +2

Counterfactual Evaluation Algorithmic Auditing Decision-Making under Uncertainty

Apr 25, 2026cs.LG

Robustness of Refugee-Matching Gains to Off-Policy Evaluation Choices

Previous research has investigated the potential of refugee matching for boosting refugee outcomes, first considered by Bansak et al. (2018). This paper demonstrates the stability of counterfactual impact evaluation results in the context of refugee matching in the United States using a range of off-policy evaluation methods. In order to estimate counterfactual impact and test the robustness of our results, we employ several evaluation methods, including inverse probability weighting (IPW) and multiple variants of augmented inverse probability weighting (AIPW). We also consider various modifications, including alternative modeling architectures and different assignment procedures. The impact estimates remain consistent in magnitude in all scenarios as well as statistically significant in most cases. Furthermore, the estimates are also consistent with the results originally presented in Bansak et al. (2018).

Kirk Bansak, Elisabeth Paulson, Dominik Rothenhäusler +3

Immigration Policy Lab, Stanford University · Department of Political Science, University of California, Berkeley · Technology and Operations Management Unit, Harvard Business School +3

Counterfactual Evaluation Causal Effect Estimation Off-Policy Evaluation