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

Oct 7, 2026cs.LG

Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation

Off-policy evaluation (OPE) estimates the value of a target policy from logged data, but limited behavior-policy coverage can force high-variance reweighting or reward-model extrapolation. Counterfactual annotations can add evidence about unobserved actions, yet practical sources, including domain experts and large language models (LLMs), may be costly, biased, or noisy. We study budgeted acquisition of such annotations for contextual-bandit OPE. Given source-specific costs and error profiles, we formulate an integer allocation problem over context-action pairs and annotation sources to minimize the component of estimator variance that depends on the annotation plan. We characterize when annotations are valuable through a first-annotation threshold and local annotation-value regimes. For the coupled multi-source problem, we develop a majorization-minimization algorithm with dynamic-programming subroutines that monotonically improves the objective. Experiments in synthetic clinical and LLM-annotated education bandits show that our allocation method reduces fixed-profile mean squared error (MSE) by 20.58% and 10.77%, respectively, relative to no annotation.

Biao Xiang, Ali Eshragh, Yuexing Li +1

Pennsylvania State University, State College, PA · Johns Hopkins Carey Business School, Washington, DC · International Computer Science Institute, Berkeley, CA +1

Off-Policy Evaluation Counterfactual Evaluation Contextual Bandits

Oct 6, 2026cs.AI

RippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents

Agent checkpoint systems decide what state is recovery-relevant, how to snapshot it, and whether rollback is admissible. None decides which of the safe boundaries they expose are worth materializing. We formulate this as counterfactual checkpoint advantage, the reduction in future recovery cost obtained by checkpointing a candidate rather than skipping it, and measure it by driving a CP branch and a SKIP branch to the same logical failure and recovering both under matched model, tool, verifier, and stopping conditions. On a frozen pilot of 12 SWE-bench Verified tasks and 106 real recovery branches, checkpointing saves 49.4 s per task, and that figure resolves into two regimes two orders of magnitude apart. The first checkpoint returns 100.0 s on 156.5 s of protected work, a conversion of 0.64; a second one step later returns-1.1 s on 41.8 s, a conversion of -0.03. Recovery is a re-derivation rather than a replay, so preserved work is a poor guide to saved work, and the classical elapsed-work rule misprices the second checkpoint by its full nominal cost. We identify where placement can pay, and set the bar a placement policy must clear.

Mayur Akewar, Ravi Ranjan

Florida International University, Miami, USA

Software Engineering Agents Counterfactual Evaluation AI Agent Evaluation

Oct 1, 2026cs.LG

Fixing a Model That Learned Worse Cancer Means Lower Risk: Monotonic Constraints in Bladder Cancer Recurrence Prediction

Background and Objective: Clinicians expect recurrence risk to climb with cancer severity. In a UK multicentre trial, an unconstrained XGBoost model learnt that higher tumour stage and carcinoma in situ predicted lower recurrence risk, and discrimination, calibration, and SHAP were all blind to it. We developed a counterfactual testing framework to detect this inversion and a monotonic-constraint framework to remove it without hurting performance. Methods: BOXIT enrolled 472 patients with protocol-mandated cystoscopy across 51 UK sites (2007-2012); 435 had at least two years' follow-up (153 recurrences, 35.2%). We developed a counterfactual direction test and a monotonic-constraint correction, with constraint directions drawn from the EORTC and EAU risk systems, and evaluated both against unconstrained XGBoost and logistic regression on 18 predictors (seven directed) over 50 cross-validation folds. The test worsened each patient on one directed feature at a time to check whether risk fell; SHAP direction and calibration were also assessed. Key Findings and Limitations: Tumour stage and carcinoma in situ were associated with lower recurrence, opposite to medical intuition; the unconstrained model reversed carcinoma in situ counterfactuals in 90.2% of cases and stage in 74.3%. Discrimination (

Δ

AUC 0.005, p=0.47), calibration, and SHAP magnitude were all blind to the inversion. Monotonic constraints eliminated every violation at no cost to discrimination (0.723 vs 0.718) and outperformed EORTC (p=8.9e-16). Limitations: single trial, internal-external validation only. Conclusions and Clinical Implications: A model that had learned this inversion passed every conventional check. A counterfactual direction test, run as a single refit with pre-specified monotonic constraints, catches this failure at no cost to performance and should be routine before clinical deployment.

Saram Abbas, David Thomas, Naeem Soomro +3

School of Engineering, Newcastle University, Newcastle upon Tyne, UK · Electronics and Computer Science, University of Southampton, Southampton, UK · Department of Urology, Freeman Hospital, Newcastle upon Tyne, UK +1

Counterfactual Evaluation Gradient-Boosted Decision Trees Clinical Outcome Prediction Constrained Optimization Clinical Risk Prediction

Sep 29, 2026cs.LG

Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations

Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by downstream execution. Existing prompt-adaptation methods infer compression errors by comparing full-context and compressed trajectories. Such comparisons cannot isolate individual compressions and are confounded by agent stochasticity. We first find that compression degrades reliability before solvability. Using matched counterfactual continuations that compare execution from the same agent state with versus without compression, we further show that severe degradation concentrates at isolated compression events. Motivated by this finding, we propose PAIR (Prompt Adaptation using Interventional Rollouts) for adapting structured compression prompts. PAIR identifies individual compressions that degrade subsequent execution, diagnoses their effects, and revises the relevant sections of a fixed compression template. PAIR achieves the strongest cross-run reliability among compressed methods in every main benchmark-scope combination, consistently exceeding the competing prompt-adaptation baseline. Without modifying the downstream agent, PAIR brings compressed execution close to the no-compression baseline and sometimes numerically exceeds it.

Guanghui Min, Liang Wu, Mingjia Shi +4

University of Virginia · Nokia

Counterfactual Evaluation LLM Agent Evaluation Long-Horizon LLM Agents Context Compression

Sep 27, 2026cs.AI

What Happens During Autonomous Deep Research After the User Steps Away?

In autonomous deep research, a user provides a task and relevant background, then leaves the agent to conduct an extended investigation without further human intervention. We study how this initial user information is reflected in intermediate actions and how these actions relate to final recommendations. We introduce DRaligned, a counterfactual behavioral evaluation framework built on PDR-Bench. By varying one task-relevant user factor while keeping the remaining context fixed, we compare acquisition requests, working drafts, and final reports. Source-grounded extraction, blinded local judgments, and deterministic aggregation yield coarse directional measurements while leaving ambiguous cases unresolved. Our experiments show that strong user-specific delivery can emerge from a largely shared research process: agents investigate similar broad questions but allocate requests differently, and final recommendations distinguish user conditions more clearly than explicit requests do. Reports can also integrate user factors that were not jointly visible during acquisition. In readable draft-to-report comparisons, recommendations often retain their coarse user-specific direction despite substantial rewriting. Final directional differences recur across tested agent models, execution harnesses, and evaluator models, even as execution paths vary. These findings describe how initial user information shapes autonomous research and clarify the relationship between the process an agent follows and the recommendations it delivers.

Yimin Liu, Yijia Zhang, Yanmin Li +4

University of Southern California · University of Michigan, Ann Arbor · Institute of Automation, Chinese Academy of Sciences +3

Counterfactual Evaluation Deep Research Agents AI Agent Evaluation User Modeling

Sep 27, 2026cs.LG

MultiEcho: An Experimental Science of Learned Worlds

World models can be studied as experimental systems with response laws of their own. We introduce MultiEcho, a framework for estimating these laws through controlled counterfactual interventions, delimiting their applicability, and separately testing their physical correspondence. Across nine simulated physical systems and seven frozen model configurations, three-reference estimators predict complete intervention responses and recover intervention parameters. Estimator selection uses discovery data only; frozen fits are evaluated on validation and confirmation contexts. The experiments distinguish response predictability, intervention readability and physical accuracy. Responses can be locally describable yet poorly match physical effects in the same target coordinates. Event-window, visibility and camera interventions reveal conditional applicability, and paired generator configurations show reduced readability under a scene prompt with stronger guidance. Magnitude sweeps expose small image errors alongside large relative effect errors. An exact-reset material experiment separates registered visible-response success from fixed-readout failure on material-dependent futures at matched positions and velocities. Exact finite-scale identities resolve odd and even response errors; first-order remainder bounds specify when refined calibration converges. MultiEcho provides an experimental basis for studying learned-world laws independently of, and in relation to, physical laws.

Meng Zhu, Airui Zhang

SHIHAO XINRUI Group

Counterfactual Evaluation World Models World Model Evaluation

Sep 25, 2026cs.AI

Evaluating Budgeted Context Projection with Unexecuted Companion Runs

Context projection can shorten individual requests while changing whether an agent finishes within its budget. We examine how sequential evaluation obscures this trade-off when a capped first continuation prevents its companion from running. In a recorded ReVerPi source-reading campaign, 15 pairs with two final answers yield 12 historically scored successes per arm. Retaining all 27 intervention boundaries distinguishes observed failures from ten unexecuted companions and bounds projected-minus-full success between

-9

and

+1

tasks. Under the archived scoring contract, a frozen projection selector has a success difference from full context of

[-3,0]

; outside four fitting tasks, it is

[-4,-1]

across 23 boundaries. Excluding one task whose platform premise is not established by retained actor-input evidence changes the nonfitting range to

[-3,0]

across 22 boundaries, so strict inferiority is not robust to that exclusion. Among eleven historically joint-success pairs, projection uses 25% fewer aggregate logical tokens but more tokens for the median pair and 55 rather than 35 suffix requests. These retrospective results concern one adaptively assembled campaign, not population performance. The case motivates accounting that retains every boundary, preserves unknown outcomes and policy dependencies, checks task premises, and separates bounded completion from success-conditioned resource use.

Guangzhe Zhang

Independent AI Researcher

LLM Context Management LLM Agent Evaluation Context Compression Counterfactual Evaluation Long-Horizon Agent Evaluation

Sep 25, 2026cs.LG

Robust to Which Model Change? A Unified Evaluation of Robust Counterfactual Explanations

Robust counterfactual explanations promise recourse that still works after the model behind it changes. Whether they keep that promise depends on what the change is. A small perturbation of the parameters, retraining on new data, and a new architecture are different events, and each existing method is evaluated against the one it was built for. Reported robustness scores, therefore, answer different questions and cannot be compared. We propose a unified cross-family evaluation protocol that holds factual instances and generated counterfactuals fixed while testing every method against the same eight types of model change. The benchmark compares six robust methods and two standard baselines on four tabular datasets. It characterizes every changed classifier through its outputs and reports empirical robustness together with coverage, base validity, and proximity. We find that relative performance and failure modes vary across change families. Bounded parameter perturbations change 0.95% of test predictions on average, compared with 4.9% for bootstrap retraining. Methods with guarantees for these perturbations do not necessarily transfer to other changes. RobX transfers most consistently in our experiments, although greater stability can require larger interventions. We argue that robust CFE methods should be evaluated through a common protocol that specifies the model changes, measures their realized behavioral magnitude, and keeps generation performance separate from robustness.

Marcin Kostrzewa, Maciej Zięba

Department of Artificial Intelligence Wrocław University of Science and Technology

Counterfactual Evaluation Counterfactual Explanations Explainability Evaluation

Sep 17, 2026cs.LG

Correct Now, Insufficient Later: Auditing Update Sufficiency in Context Compression

A memory can answer a current query correctly while discarding distinctions required by a later update. We investigate this failure with a paired-history audit: two histories have the same current answer, receive a shared future update, and require different subsequent answers. A pilot evaluates 24 history pairs across six synthetic mechanisms, 12 memory conditions, two repeats, and two model backends. A deterministic frontier selector obtains strict reveal accuracy of 96/96 on DeepSeek and 82/96 on GLM; a structured writer obtains 62 successes with one unresolved outcome and 56/96. The configured four-outcome joint contrast has finite-sample identification intervals of [0.521, 0.542] and [0.292, 0.313], not confidence intervals. A record-level audit distinguishes retained-state adequacy, response delivery, and answer-schema compliance without changing those original scores. It finds 26 and 25 well-formed but semantically wrong structured reveal memories, while all 14 GLM frontier reveal failures contain correct values in the wrong wrapper. Tombstone removal produces 16/16 exact replay failures in the targeted mechanism. Identifier renaming then exposes a separate flaw: original frontier late-reference adequacy falls from 8/8 to 94/320 transformed instances. We provide and test a label-equivariant repair, but it preserves only 2/8 original late-reference answers: eliminating a naming shortcut does not solve unknown future relevance. These results support a scoped evaluation methodology and reproducible failure analysis, not general superiority of the repaired algorithm. Paid pilot evidence, retrospective diagnostics, and new offline tests are reported separately; no independent held-out or natural-task validation is claimed.

Guangzhe Zhang

Independent AI Researcher

Agent Memory Counterfactual Evaluation LLM Auditing Context Compression

Sep 16, 2026cs.AI

Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts

Reliable agent evaluation is complicated by automatic harness optimization, which repeatedly uses a released benchmark

B_{\mathrm{rel}}

to guide a Proposer that edits prompts, memory, retrieval, tools, and control code around a fixed foundation model. Task holdout is commonly used to guard against harness overfitting. It varies semantic tasks but leaves the benchmark protocol fixed, so a bad genius Proposer can produce a cheating harness whose improvement over the initial harness on

B_{\mathrm{rel}}

depends on a benchmark-wide shortcut. We introduce Counterfactual Harness Search and Evolution (CHASE), which casts harness evolution as constraint generation over valid counterfactual benchmarks. After each Proposer update, a Challenger searches for an executable protocol transformation with large gain destruction. A validity firewall checks that task semantics are preserved, while a held-out confirmation set determines whether the counterfactual enters a finite archive. We formalize an ideal shortcut-neutralized benchmark

B_0

and establish theoretical guarantees linking finite counterfactual archives to

B_0

and characterizing sequential Challenger search. We evaluate CHASE on Syn-Ledger and OfficeQA, where CHASE retains strong released-benchmark gains while substantially reducing gain destruction under valid protocol transformations.

Guojun Zhu, Xunheng Huang, Peng Yin +3

School of Mathematical Sciences, University of Chinese Academy of Sciences, China · Department of Statistics & Data Science, National University of Singapore, Singapore · Institute of Automation, Chinese Academy of Sciences, China

Counterfactual Evaluation Benchmark Construction LLM Agent Evaluation Agent Harness Optimization

Sep 15, 2026cs.CL

EviScope: Paired Counterfactual Evidence Diagnostics for Faithful and Efficient Grounded Language Models

Grounded language-model systems are often evaluated by final answer accuracy, yet a correct answer can be unsupported, drawn from the wrong source, or produced when evidence is insufficient or contradictory. We introduce EviScope, a paired counterfactual benchmark that holds the question fixed while adding, removing, distracting, or contradicting its evidence. EviScope-v1.1 contains 40 four-condition quartets with repaired counterfactual claims and span-level support labels for automatic evaluation. Across 960 gold-blind generations from Qwen2.5-7B, Llama 3.1 8B, and Gemini 3.5 Flash, paired metrics expose model-dependent grounding behavior that answer accuracy hides. On two local open models, an explicit evidence-action gate underperforms vanilla RAG on QCS: 0.15 vs. 0.50 for Qwen and 0.10 vs. 0.375 for Llama. Gemini reaches 0.944 joint success under both prompts, yet still answers 5% of conflict cases after contradiction insertion. EviScope therefore distinguishes unsupported answering, conflict blindness, and wrong non-answer actions rather than scoring answers alone.

Suryadeep Singh Deswal

Indian Institute of Technology Roorkee Roorkee, India

Counterfactual Evaluation LLM Grounding Language Model Generation Evaluation Knowledge Conflicts in Language Models Evidence-Grounded Generation

Sep 15, 2026cs.SD

CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection

Spoken sarcasm detectors may exploit lexical content, prosody, or their interaction, yet conventional evaluation cannot reveal which cues drive their predictions. We introduce CLASH (Controlled Lexical-Acoustic Separation Harness), a bilingual counterfactual diagnostic framework that evaluates each utterance under original, lexical-preserving, prosody-preserving, and approximately neutralised conditions. We evaluate handcrafted acoustic-feature systems, self-supervised learning (SSL) probes, and large audio language models (LALMs) on CMMA and MUStARD. For target-only Qwen3-Omni, lexical-preserving speech retains a 0.135--0.148 AUROC advantage over prosody-preserving speech after duration balancing, with cluster-bootstrap intervals above zero; alternative lexical resynthesis preserves this advantage. Acoustic interventions shift scores without consistently improving discrimination or changing binary predictions under the evaluated conditions. Context and interaction estimates vary across corpora. These findings distinguish acoustic sensitivity from sarcasm discrimination while exposing duration, identity, and transformation effects.

Qiyang Sun, Xudong Li, Yupei Li +4

Imperial College London · New York University · Technical University of Munich +3

Audio-Language Model Evaluation Counterfactual Evaluation Speech Prosody

Sep 12, 2026cs.LG

Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance Variables

Machine learning models can achieve strong test performance while relying on demographic or acquisition-related shortcuts. We propose counterfactual (CF) marginalisation as a test-time evaluation procedure for assessing robustness of classification models to such variables. Given a CF image generator, we intervene on nuisance parent variables such as age or sex, generate CF versions of each test image, and average predictions over a target intervention distribution. This produces intervention-aware predictions that marginalise demographic effects while preserving patient-specific latent information. We use these predictions to define metrics for CF risk, calibration, stability and worst-case sensitivity. We demonstrate this framework's utility for quantitative robustness evaluation.

Yasin Ibrahim, Hermione Warr, Robin J. Evans +1

Department of Engineering Science, University of Oxford, Oxford, UK · Department of Statistics, University of Oxford, Oxford, UK

Counterfactual Evaluation Classification Spurious Correlation Robustness

Sep 11, 2026cs.LG

Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation

Continual world models must decide whether new data justify changing the model. Fixed replay schedules and prediction-error triggers specify when to update, but neither reveals the value of an individual update: one deployment run cannot show how the same model would have performed at that moment had it held its parameters. We introduce the fork ledger, which branches a deployment stream at pre-registered decision points into matched update and hold continuations under common random numbers. It evaluates both continuations on the same episodes and records

\Delta R = R_{\mathrm{update}} - R_{\mathrm{hold}}

. Always applying one fixed update mechanism lowers return on all three simulated control tasks: CartPole (

-144.0

; checkpoint-bootstrap

95\%

CI

[-185.4,-116.1]

, against a converged return near

650

), Walker (

-82.8

;

[-101.1,-61.7]

) and Cheetah (

-18.6

;

[-29.0,-6.6]

). Divergence is an outcome of applying the update, so the estimand counts every attempted fork; restricted to the

693

of

720

that did not collapse, CartPole and Walker are unchanged in sign (

-113.4

and

-82.1

) and Cheetah becomes unresolved (

-3.9

;

[-17.5,+13.0]

). The task is the unit of inference: each contributes

240

attempted forks over five pretrained checkpoints crossed with two drift directions. The ledger makes counterfactual utility observable for a fixed mechanism, allowing triggers to be judged by the updates they select rather than by surprise detection alone.

Anqi Peter Li, Kaden Kim

Substrate Labs · UC Berkeley

Counterfactual Evaluation World Model Learning Continual RL Model-Based RL

Sep 8, 2026cs.CL

What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory

Agent memory systems must discard stored information when their history exceeds a fixed token budget. Existing budget-accuracy frontiers quantify the resulting loss in accuracy, but do not distinguish irreversible losses caused by eviction from recoverable retrieval failures. We introduce the restore counterfactual, a per-question paired intervention that reinstates the question's gold evidence in the read-time context and reruns the same reader. Combining the change in correctness with whether the evidence was retained after eviction classifies each oracle-answerable error as recoverable, irreversible, or residual; in the residual case, the answer remains incorrect after restoration. We evaluate FIFO, random, redundancy-aware, and LLM-importance eviction on LongMemEval-S at three budgets and under two retrieval regimes, using GPT-4o-mini as the primary reader and judge and GPT-5.4-mini as a robustness reader. Under top-k retrieval at an 80k-token budget, the irreversible share among errors corrected by restoration is 0.67-0.73 for FIFO, random, and redundancy-aware eviction, compared with 0.60 for LLM-importance. At 8k tokens, it reaches 1.00 for all four policies. Recoverable errors occur under top-k retrieval at 80k tokens but are absent under forced-gold injection by construction, so budget-accuracy results are not directly comparable unless the retrieval regime is reported. An exploratory matched-accuracy analysis detects no difference in irreversible rate among accuracy-matched policy pairs at a resolution of 1.2-6 percentage points. The same analysis detects the deliberately destructive control. To our knowledge, this is the first per-item, per-question restore-counterfactual audit of eviction for external agent-memory stores on a standard conversational benchmark.

Chen Shen

Megagon Labs

Counterfactual Evaluation LLM Agent Memory Agent Memory Management

Sep 3, 2026cs.AI

Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing

An image editor may satisfy every regional plausibility constraint separately even when no single latent explanation fits the complete output. We formalize this local-to-global failure using a common witness grade and witness nerve. The framework separates auditing from causal identification: shared exogeneity alone allows every coupling of the regime marginals, whereas an externally justified witness relation yields sharp partial-identification bounds for prespecified image features. Helly-type arguments provide short incompatibility certificates for quasiconvex losses, heterogeneous action strata, and finite witness atlases; a blocker-hypergraph formula gives exact repair counts. Simultaneous confidence regions for the regime marginals give finite-sample outer coverage of the complete identified interval. Controlled MNIST, Morpho-MNIST, and smallNORB studies demonstrate the predicted local-global separation, while synthetic experiments test sharp bounds, certificate recovery, and structured computation. The method audits a declared feature relation and does not identify unrestricted pixel-level counterfactuals.

Usef Faghihi, Amir Saki

Department of Mathematics and Computer Science, Université du Québec à Trois-Rivières, Trois-Rivières, Quebec, Canada

Counterfactual Evaluation Causal Inference

Sep 2, 2026cs.CL

Counterfactual Fairness Audits of Multi-Step Clinical LLM Agents Require a Measured Per-Action Instability Floor

Counterfactual audits are the standard tool for checking whether a clinical agent treats demographically distinct but clinically identical patients differently. They report a flip rate: how often an action changes when only the patient descriptor changes. We show that this quantity is uninterpretable on its own. Re-running an identical condition ten times over sixteen vignettes (same narrative, same descriptor string, nothing varied) moved a clinical agent's action in 8.7% of outcome-vignette cells, and instability was heterogeneous across actions by a factor of eight, from 0.022 for ICU escalation to 0.179 for controlled-substance caution. No demographic contrast in our data was distinguishable from that floor. A second model gives a pooled floor of 6.7% and ranks the six actions almost identically (Spearman 0.94, exact p=0.017), so the floor is not one system's artefact. Majority-vote aggregation over five draws removes 39% of it and then flattens, and a null simulation attributes the residue to heterogeneous per-cell rates, so replication mitigates without eliminating. Any counterfactual fairness estimate reported without a per-action floor beside it therefore cannot be read as evidence of disparity. The measurements were taken with FairMedAgent, an evaluation harness for disparity in the actions of clinical LLM agents whose estimand, the within-range counterfactual flip rate, counts only flips between actions a published decision rule admits and a clinician has adjudicated. That estimand requires band adjudication, which is under way; no disparity result is claimed here. Each synthetic vignette runs a six-stage trajectory (five model-facing decisions around a deterministic environment step) under fixed-form conditions spanning race, sex, age, insurance, English proficiency, and their intersections. The harness, the floor protocol, and every analysis script are released.

Rohith Reddy Bellibaltu, Manpreet Singh, Deepak Parashar +1

Florida International University · Boston University, Boston, MA 02215 USA · Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India +1

Counterfactual Evaluation Algorithmic Fairness Counterfactual Fairness Clinical Language Model Evaluation LLM Agent Reliability

Aug 12, 2026cs.LG

Learning Under Treatment-Induced Label Indeterminacy with Expert Annotations of Counterfactual Outcomes: A Case Study in Neurological Prognostication

Clinical prediction models are often developed as if the outcome of interest were cleanly observed for every patient. This assumption fails when treatment decisions make the clinically relevant outcome permanently unobservable. As a case study of this problem, we consider post-cardiac-arrest neurological prognostication using a cohort of 2,497 patients, including 1,429 patients whose outcomes were rendered indeterminate by treatment decisions. These patients with indeterminate outcomes were reviewed by independent clinical experts, who provided their guesses of counterfactual outcomes about what would have happened to the patients. We refer to these patients as uncertain cases. We also have patients for whom we observe their clinically relevant outcomes; we refer to these patients as certain cases. We propose a framework for evaluating prediction models that explicitly splits the evaluation between certain and uncertain cases. Here, we cannot easily evaluate both types of cases in a uniform manner as the available target labels differ. We then propose a simple prediction model that uses target labels from both certain and uncertain cases in a manner that allows us to trade off between them. Across the proposed neural model and a collection of tabular baselines, models with similar certain-case AUROC can nevertheless differ substantially in both certain-case Brier score and their probability estimates for uncertain cases. Improving alignment with target labels of uncertain cases for our proposed model generally comes at the cost of worse accuracy on certain cases, highlighting an explicit tradeoff that standard evaluation conceals. These results show that when treatment decisions determine whether clinically meaningful outcomes remain observable, conventional evaluation metrics can miss important failure modes in the very patients for whom prognostic support matters most.

Xiaobin Shen, Chloe Y. H. Huang, Jonathan Elmer +1

Heinz College of Information Systems and Public Policy, Carnegie Mellon University · Department of Emergency Medicine, University of Pittsburgh

Counterfactual Evaluation Clinical Outcome Prediction Counterfactual Prediction Selective Labels

Aug 12, 2026cs.LG

Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversion

Graph Neural Networks (GNNs) achieve strong predictive performance on graph-structured data across domains such as chemistry, biology, and network analysis, yet they provide no intrinsic explanation of their predictions. This limits their adoption in high-stakes and safety-critical settings. Counterfactual explanations address this by revealing the minimal structural modifications that would change a model's prediction. On graphs, however, such a modification is hard to produce. The search space is discrete and combinatorial, and a valid answer must respect categorical node and edge types together with domain rules such as chemical valency in the case of molecular graphs. Existing explainers give up one of two things. Either edits are not held on the data manifold, or the search does not span the full edit space. We propose Graph Diffusion Counterfactual Explanation via Inversion (GDCE-I), which gives up neither. A discrete denoising diffusion model with a novel discrete inversion scheme enables distribution-aware edits leveraging the whole domain edit space. We further address the incomplete and inconsistent evaluation of graph counterfactuals by deriving a framework of explanation desiderata and applying it to every method under one shared protocol. Across four benchmarks, GDCE-I outperforms related work by a large margin on the defined framework. For the molecular domain, we further qualitatively show that GDCE-I attains interpretable in-distribution solutions.

David Bechtoldt, Sidney Bender

Machine Learning Group, TU Berlin, 10587 Berlin, Germany · BIFOLD–Berlin Institute for the Foundations of Learning and Data, Berlin, Germany

Counterfactual Evaluation Counterfactual Explanations GNN Explainability Graph Diffusion

Aug 12, 2026cs.SD

Do Text-to-Music Models Really Follow Instructions? A Counterfactual Evaluation of Key and Beat Grouping

Prompted attribute agreement is widely used as evidence of text-to-music controllability, yet a requested attribute may occur simply because it is already common in the model's output distribution. We introduce a matched counterfactual evaluation that separates target occurrence from instruction-attributable control. Each family contains a neutral input that omits the scored attribute and two otherwise matched inputs that swap the requested target. All three are rendered through frozen native-interface adapters with a shared seed. Applied to global key and beat grouping in three open systems, this design changes the empirical conclusion. ACE-Step 1.5 and Stable Audio 3 Medium exhibit substantial key control, whereas LeVo2 does not. For beat grouping, the same models redirect toward the rare three-beat target, but high four-beat agreement is largely inherited from neutral outputs: Stable Audio 3 produces four-beat grouping in 0.97 of neutral cases but only 0.56 under its explicit four-beat treatment. Off-attribute placebos, external recognizer validation, blind expert annotation, and multi-seed sentinels support the attribution. When targets have unequal output priors, agreement describes what a model produced, while matched neutral and target-swap contrasts test whether the instruction changed it.

Yining Wang

Bilibili Inc.

Text-to-Music Generation Music Generation Evaluation Counterfactual Evaluation Controllable Music Generation

Aug 12, 2026cs.CV

How Can Driving World Models Do Counterfactual Prediction?

Driving world models are often interpreted as counterfactual simulators for observed driving episodes: given a factual driving log, they are asked what would have happened under an alternative ego action. In this paper, we identify a fundamental mismatch between this goal and direct action-conditioned prediction. The direct prediction uses the shared history and the alternative action but not the factual continuation observed after that history. It can therefore generate a plausible future without preserving what actually happened in this episode. We formalize this gap using the causal recipe of abduction, action, and prediction and study it in a setting with a short time horizon, where the alternative ego action does not alter how surrounding agents evolve. To make the gap measurable, we construct a controlled simulation benchmark with factual outcomes and matched counterfactual outcomes. Across two representative world models, direct predictions fail to match the counterfactual ground truth, supporting our analysis. As a constructive check of this analysis, we introduce a deliberately simple, training-free pipeline that moves observed evidence into the counterfactual view and lets the frozen model complete what remains unknown. Even this simple construction raises the overall recovered fraction substantially and reduces perceptual distance to the matched counterfactual on both models. We hope this work draws attention to this gap and motivates better counterfactual prediction methods for driving world models.

Jiaru Zhang, Can Cui, Yi Xu +3

Purdue University · Bosch Center for Artificial Intelligence

Counterfactual Evaluation Causal Counterfactual Generation Counterfactual Prediction World Models for Autonomous Driving Causal Inference

Aug 11, 2026cs.LG

Unmasking Toxic Mimicry in Medical Offline Reinforcement Learning for ICU Sepsis Management via Counterfactual Clinical Audits

Offline reinforcement learning (RL) offers considerable promise for optimizing ICU treatment decisions, yet standard evaluation metrics Mean Squared Error (MSE) and Fitted Q-Evaluation (FQE) assess only behavioral imitation and cannot detect Toxic Mimicry, a failure mode in which agents replicate harmful patterns such as treatment withdrawal during comfort-care transitions. Using the MIMIC-III database, we propose the Counterfactual Clinical Audit (CCA) framework, which stress-tests RL agents through physiological perturbations anchored in Surviving Sepsis Campaign (SSC) guidelines. We audit a Medical Decision Transformer (MedDT) and a Historical Causal Transformer (HCT-RL), the latter employing Causal Action Shielding, propensity-based importance weighting, and Conservative Q-Learning. CCA reveals that MedDT paradoxically reduces vasopressor dosage as lactate escalates, contradicting resuscitation guidelines, while HCT-RL maintains physiologically consistent responses. These findings expose a systemic misalignment between statistical fit and clinical safety, supporting counterfactual audits as a necessary evaluation standard for medical RL.

Hangqi Ren, Junyi Liao

School of Engineering, Vanderbilt University, Nashville, TN, USA · Pratt School of Engineering, Duke University, Durham, NC, USA

Counterfactual Evaluation Offline RL Safe RL

Aug 11, 2026cs.CV

FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding

Counterfactual video understanding evaluates whether models grasp physical and commonsense regularities. However, existing multiple-choice question (MCQ) benchmarks inadvertently leak target events through their questions and candidate options. This reduces the core challenge from active discovery to text-guided verification. In this paper, we present FADE, an effective training framework for counterfactual discovery and explanation. Our method is built on an evidence-first, two-stage training paradigm. First, evidence-internalized supervised fine-tuning grounds the model's predictions in decisive visual anomalies. Second, we apply a fading-anchor reinforcement learning strategy that progressively removes textual guidance, compelling the model to independently discover and explain evidence. To rigorously evaluate this capability, we also introduce an effective pipeline that converts existing MCQ datasets into aligned MCQ, open-ended question answering (OQA), and captioning tasks without requiring additional data curation. Our simple approach yields strong results. Using Qwen3-VL-8B as the baseline, FADE achieves state-of-the-art strict paired scores across all three tasks on DualityVidQA-test and IPV-Bench, outperforming GPT-5.6. In specific, when transitioning from constrained MCQs to unconstrained OQA and captioning, our model demonstrates remarkable robustness. Its performance retention is 90.4% and 67.4% on DualityVidQA-test-substantially higher than the 48.1% and 30.7% retained by GPT-5.6. We hope this simple framework can serve as a solid baseline for future research in unconstrained counterfactual video understanding.

Fufangchen Zhao, Jinhu Fu, Jiachen Lei +3

State Key Laboratory of Networking and Switching Technology, BUPT · AMAP, Alibaba Group

Counterfactual Evaluation Video QA Causal Reasoning in Videos

Aug 10, 2026cs.LG

Twin Rollouts: Noise-Coupled Counterfactual Branching in Interactive Video World Models

Interactive video world models generate rollouts autoregressively under an action stream, yet they are trained and evaluated almost exclusively on factual prediction. We study counterfactual generation inside the rollout: given a trajectory the model has itself generated, what would have happened had the actions differed from step t* onward? We formalize noise-coupled twin rollouts --- a factual and a counterfactual branch sharing the generated prefix and the future exogenous noise sequence, diverging only in the action stream at an intervention point. Because the factual branch is self-generated, its exogenous noise is known exactly: the abduction step of Pearl's counterfactual procedure is exact by construction, sidestepping the approximate-inversion problem faced by editing-based pipelines. Noise coupling further turns the minimal-change principle into a per-sample verifiable property: we define a spatiotemporal locality metric that penalizes divergence outside the causal descendants of the intervention, computable against simulator ground truth without a learned judge. Forking the simulator state at t* yields ground-truth counterfactual re-renders, which we use as verifiable rewards for post-training. This note establishes the formal framework, metric definitions, and positioning; experiments are forthcoming.

Yu Ma, Hongli Shi, Xinran Xu

Action-Conditioned Video Generation Counterfactual Evaluation Causal World Models Causal Counterfactual Generation Video Generation Video World Models

Aug 4, 2026cs.CL

SocietyBench: Forecasting Counterfactual Social-World Evolution

Large language models (LLMs), and the agents built on top of them, are now benchmarked heavily on whether they can finish a task -- fix a bug, drive a browser, operate a GUI. A complementary social ability, namely how well a model understands and forecasts the way real social events unfold, has barely been measured. We introduce SocietyBench, an end-to-end benchmark that takes a one-line event topic, collects Web news and social-media posts across five platforms, distills them into a date-indexed timeline that keeps factual events and a public-opinion layer separate, and then turns every cutoff date on that timeline into an audited bank of forecasting questions. Questions are scored on two orthogonal 100-point axes: probability calibration and temporal accuracy. Before any model sees a timeline, a three-phase procedure replaces every named entity and shifts every date by a per-event constant, turning a real arc into a counterfactual social world -- structurally identical to what happened, but stripped of the surface labels a model could match against pre-training memory. On five heterogeneous events and 125 prediction points in Chinese and English editions, the strongest of six frontier LLMs reaches only 75.0 out of 100, against a trivial anchor of 50. The two axes come apart: a model can be calibration-strong but time-weak, or the reverse. Three agent frameworks built on a shared base model fail to improve on that base, and two model-free heuristics trail every LLM. Per-event gaps reach 21.4 points on a single axis, which is our main argument for evaluating on several events rather than one. All anonymized timelines, question banks, ground truth, and scoring code are released.

Zhenran Wang, Zhonghan Bian, Jinsong Li +1

Counterfactual Evaluation Forecasting Benchmarks Probabilistic Forecasting Language Model Calibration

Aug 4, 2026cs.AI

Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning

Applying a valid medication-safety rule when its patient-specific conditions are not met can produce an incorrect decision. Existing medical evaluations largely use isolated and fixed scenarios. A model may therefore answer correctly by recalling a drug-risk association without showing that it used patient information to decide whether the rule applies. To address this gap, we introduce MedPIC-Bench, a benchmark of source-verifiable recommendations and expert-validated questions for patient-specific medication-safety reasoning. It combines guideline-following questions with paired counterfactual questions in which a controlled change in patient information changes whether a rule applies. The benchmark contains 467 questions annotated along six clinical and reasoning dimensions. Across 28 medical-specific, general, and proprietary LLMs, every model performs worse on counterfactual questions, with mean accuracy falling from 63.6% to 45.1%. Models perform well when an explicit patient attribute directly signals a familiar contraindication, but struggle when patient information must narrow or withdraw a safety warning. Model rationales often acknowledge the changed patient information, yet the final answers retain the previous safety judgment. This vulnerability persists among medical-specific LLMs, whose average CF performance trails that of general LLMs. MedPIC-Bench therefore makes conditional rule application measurable and highlights the limitations of static medication-safety accuracy for assessing patient-specific reliability.

Zhitian Hou, Yuhang Liu, Pengkai Wang +8

The Hong Kong Polytechnic University · Sun Yat-sen University

Counterfactual Evaluation Healthcare Clinical Decision Support Medical Reasoning Clinical Language Model Evaluation

Jul 31, 2026cs.AI

A Generalized-Bayes Perspective on Counterfactual Explanations: Posterior-Based Decision-Making and Evaluation

Counterfactual explanations (CEs) enhance the interpretability of machine learning models by identifying the smallest change to an input required to obtain a desired output. Although CEs are conventionally formulated as a distance-minimization problem, the theoretical basis of this formulation has received limited attention. We show that a distance-minimization-based CE is mathematically equivalent to the maximum a posteriori (MAP) estimate of a Gibbs posterior within the generalized Bayes framework, specifically when a distance-based prior is used. We call this formulation the Distance-Prior Generalized Bayes CE (DP-GBCE). Building on this posterior perspective, we introduce two decision rules beyond MAP within a unified framework: a Bayes decision that minimizes expected decision loss and CVaR-CE, a risk-averse decision rule. We also propose an extension that uses Bayesian model weights to mix the posterior distributions of multiple models, thereby accounting for model multiplicity, where several models have comparable predictive performance. Finally, we define metrics for evaluating both individual CEs and the posterior distribution as a whole, and use experiments on simulated data and Google Trends data to quantify the trade-offs among the decision rules.

Keita Kinjo

Faculty of Business, Kyoritsu Women’s University

Counterfactual Evaluation Counterfactual Explanations Bayesian Inference Bayesian Decision Theory Decision-Making under Uncertainty

Jul 29, 2026cs.LG

DoTime: A Synthetic Benchmark Generator for Interventional and Counterfactual Time Series

Most benchmarks for causal inference over time series are observational, small, or domain-specific, leaving interventional and counterfactual estimation under-served exactly where it matters most, such as in healthcare, policy evaluation, and climate science. We introduce \textbf{DoTime}, an open, scalable, and theoretically grounded generator of multivariate temporal structural causal models (TSCMs) with interventions, released as the \code{dotime} PyPI package together with four frozen evaluation suites. Beyond existing work, it adds capabilities absent from prior generators: continuous-time intervention \emph{windows}, counterfactual sampling modes with a positivity guard, regime-switching SCMs as a strict generalization of interrupted time series, non-stationary dynamics by construction with switching SCM parameters, and deterministic ramp and sinusoidal intervention profiles that place trends and structural breaks \emph{inside} the evaluation window. Moreover, it demonstrates the suitability of the generator as a prior for a causal foundation model reference implementation. The released suites span a training-scale snapshot of

100{,}000

trajectories and eight named identification structures, each with exact ground truth: paired interventional trajectories from the same SCM throughout, and shared-noise counterfactuals in the continuous-time suite. We ship reference baseline implementations with an evaluation harness, and pose a falsifiable claim: interventional training buys a measurable direction-accuracy advantage over an observational model of identical capacity. It is tested across three training seeds per arm. Under structure-matched evaluation on held-out episodes, the interventional prior-fitted network's (PFN) gap is positive in every structure, trajectory length, and seed tested.

Dennis Thumm, Billy Tim Anthony, Ying Chen

National University of Singapore, Singapore, Singapore

Counterfactual Evaluation Structural Causal Models Time-Series Causal Discovery Causal Counterfactual Generation Synthetic Benchmark Generation Causal Intervention

Jul 24, 2026cs.LG

CEL: Comprehensive Counterfactual Explanations Library and Benchmark

Counterfactual explanations are a prominent approach in explainable artificial intelligence (xAI), providing actionable guidance on what input changes would alter a model's prediction to a desired outcome. While early methods primarily focused on minimal feature changes, recent work incorporates additional properties such as sparsity, actionability and plausibility. Despite this progress, fair and systematic evaluation remains challenging. Existing studies often rely on different data splits, predictive models, and evaluation metrics, which limits objective comparison across methods. To fill this gap, we introduce CEL (Counterfactual Explanations Library), a unified library and benchmark for counterfactual explanations designed to support consistent implementation and evaluation. CEL includes 18 datasets of varying size and complexity and provides implementations or reimplementations of 14 widely used counterfactual methods. Using this standardized setup, we conduct a comprehensive quantitative comparison across a variety of methods on datasets that differ in size, number, and types of attributes. The evaluation protocol incorporates multiple complementary metrics capturing validity, coverage, sparsity, proximity, and distributional plausibility, including density- and outlier-based measures to assess the realism of generated counterfactuals. To the best of our knowledge, this is the first comprehensive benchmark that systematically evaluates recent counterfactual explanation methods within a unified and reproducible framework. While prior libraries and benchmarking efforts exist in the literature, many are outdated, limited in scope, or lack consistent evaluation protocols. The proposed benchmark aims to improve reproducibility, enable fair comparison, and establish a workbench for the development of future counterfactual explanation methods.

Oleksii Furman, Łukasz Lenkiewicz, Marcel Musiałek +1

Wrocław University of Science and Technology, Wrocław, Poland

Counterfactual Evaluation Explainable Artificial Intelligence Counterfactual Explanations Benchmark Design

Jul 23, 2026cs.AI

When Is a Learned Command Adapter Worth It? Closed-Loop Identification and Counterfactual Auditing of Frozen Locomotion Policies

Adding a learned adapter to a frozen, command-conditioned locomotion policy is worthwhile only if the interface exposes improvements that are both real and recoverable from deployment-time observations. We introduce an adapter necessity audit that separates global operating-point gain,same-state counterfactual headroom, deployment gain over a cross-fitted fixed action, and state-allocation gain over a frequency-matched randomized policy. Source-cluster learner refits map these quantities and constraint violations to a GO/NO-GO/ABSTAIN decision. Closed-loop command- response identification provides optional decision features. On Go2, an archived scale-prefix diagnostic finds 5.2% same-state headroom but only 0.55% recovered allocation gain. Our confirmatory audit evaluates direct, scale, heading, and yaw interventions on twenty independent clusters for each of three query distributions induced by direct control, VGCC, and MPC, using 200 full learner refits. At 1% deployment and allocation thresholds and a 5% violation tolerance, direct queries return NO-GO, while VGCC and MPC queries ABSTAIN. VGCC has the largest mean deployment gain (1.34%), but its allocation lower bound is 0.09% and its violation upper bound is 6.25%. A deployment-representative twenty-cluster H1 audit also returns NO-GO, whereas a learner-level synthetic control returns GO. The audit therefore tests whether observable signal justifies state-dependent adaptation rather than presuming that an adapter is valuable.

Zongtan Li

Counterfactual Evaluation Humanoid Robot Locomotion Robot Policy Adaptation Robotic Policy Evaluation