Counterfactual Reasoning

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

2 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 97 papers with code (219 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Counterfactual Phenotyping with Censored Time-to-Events
  22 Feb 2022 3 repositories listed
  Estimation of treatment efficacy of real-world clinical interventions involves working with continuous outcomes such as time-to-death, re-hospitalization, or a composite event that may be subject to censoring.
• Explaining by Removing: A Unified Framework for Model Explanation
  21 Nov 2020 3 repositories listed
  We describe a new unified class of methods, removal-based explanations, that are based on the principle of simulating feature removal to quantify each feature's influence.
• Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning
  6 Oct 2020 3 repositories listed
  First, we propose reward machines, a type of finite state machine that supports the specification of reward functions while exposing reward function structure.
• Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
  19 Oct 2018 3 repositories listed
  We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over other agents' actions.
• GCAN: Generative Counterfactual Attention-guided Network for Explainable Cognitive Decline Diagnostics based on fMRI Functional Connectivity
  4 Mar 2024 2 repositories listed
  Furthermore, to tackle the difficulty in the generation of highly-structured and brain-atlas-constrained FC, which is essential in counterfactual reasoning, an Atlas-Aware Bidirectional Transformer (AABT) method is…
• Do We Fully Understand Students' Knowledge States? Identifying and Mitigating Answer Bias in Knowledge Tracing
  15 Aug 2023 2 repositories listed
  Existing models tend to memorize the answer bias as a shortcut for achieving high prediction performance in KT, thereby failing to fully understand students' knowledge states.
• Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning
  3 Mar 2022 2 repositories listed
  We propose to incorporate the learner's current understanding of the robot's decision making into our model of human IRL, so that a robot can select demonstrations that maximize the human's understanding.
• COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
  23 Feb 2022 2 repositories listed Syntology ran 1 of 6 samples · 5 unverified
  Many applications of text generation require incorporating different constraints to control the semantics or style of generated text.
• Counterfactual Explainable Recommendation
  24 Aug 2021 2 repositories listed
  Technically, for each item recommended to each user, CountER formulates a joint optimization problem to generate minimal changes on the item aspects so as to create a counterfactual item, such that the recommendation…
• Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
  28 Sep 2020 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  On one hand, it has a harmful causal effect that misleads the tail prediction biased towards the head.
• Transformers as Soft Reasoners over Language
  14 Feb 2020 2 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  However, expressing the knowledge in a formal (logical or probabilistic) representation has been a major obstacle to this research.
• Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering
  12 Jun 2025 1 repository listed
  This paper introduces a method to enhance a neuro-symbolic model for counterfactual reasoning, leveraging symbolic reasoning about causal relations among events.
• Diffusion Counterfactual Generation with Semantic Abduction
  9 Jun 2025 1 repository listed Syntology ran 0 of 9 samples · 9 unverified
  Counterfactual image generation presents significant challenges, including preserving identity, maintaining perceptual quality, and ensuring faithfulness to an underlying causal model.
• Counterfactual reasoning: an analysis of in-context emergence
  5 Jun 2025 1 repository listed Syntology ran 5 of 16 samples · 11 unverified
  We show that language models are capable of counterfactual reasoning in this controlled setup and provide insights that counterfactual reasoning for a broad class of functions can be reduced to a transformation on…
• Causal Cartographer: From Mapping to Reasoning Over Counterfactual Worlds
  20 May 2025 1 repository listed
  Causal world models are systems that can answer counterfactual questions about an environment of interest, i.
• Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer
  14 May 2025 1 repository listed
  These results highlight the potential of counterfactual reasoning to enhance reinforcement learning agents' performance and generalization capabilities.
• Exogenous Isomorphism for Counterfactual Identifiability
  4 May 2025 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  This paper investigates ∼_(ℒ₃)-identifiability, a form of complete counterfactual identifiability within the Pearl Causal Hierarchy (PCH) framework, ensuring that all Structural Causal Models (SCMs) satisfying the given…
• A Causal Framework to Measure and Mitigate Non-binary Treatment Discrimination
  28 Mar 2025 1 repository listed
  Fairness studies of algorithmic decision-making systems often simplify complex decision processes, such as bail or loan approvals, into binary classification tasks.
• Neutralizing Bias in LLM Reasoning using Entailment Graphs
  14 Mar 2025 1 repository listed
  Extensive evaluations show that our framework can significantly reduce hallucinations from attestation bias.
• Controllable Sequence Editing for Biological and Clinical Trajectories
  5 Feb 2025 1 repository listed Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
  These concepts allow CLEF to apply targeted edits to the affected time steps and variables while preserving the rest of the sequence.
• Counterfactual Situation Testing: From Single to Multidimensional Discrimination
  3 Feb 2025 1 repository listed
  ST finds for each complainant similar protected and non-protected instances in the dataset; constructs, respectively, a control and test group; and compares the groups such that a difference in outcomes implies a…
• OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions
  24 Nov 2024 1 repository listed
  We anticipate that the challenges posed by OccludeNet will stimulate further exploration of causal relations in occlusion scenarios and encourage a reevaluation of class correlations, ultimately promoting sustainable…
• Gumbel Counterfactual Generation From Language Models
  11 Nov 2024 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Based on this observation, we propose a framework for generating true string counterfactuals by reformulating language models as a structural equation model using the Gumbel-max trick, which we called Gumbel…
• Causal Responsibility Attribution for Human-AI Collaboration
  5 Nov 2024 1 repository listed
  As Artificial Intelligence (AI) systems increasingly influence decision-making across various fields, the need to attribute responsibility for undesirable outcomes has become essential, though complicated by the complex…
• Fighting Spurious Correlations in Text Classification via a Causal Learning Perspective
  1 Nov 2024 1 repository listed
  In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels.
• Causality-Enhanced Behavior Sequence Modeling in LLMs for Personalized Recommendation
  30 Oct 2024 1 repository listed
  Recent advancements in recommender systems have focused on leveraging Large Language Models (LLMs) to improve user preference modeling, yielding promising outcomes.
• CausAdv: A Causal-based Framework for Detecting Adversarial Examples
  29 Oct 2024 1 repository listed
  This vulnerability of adversarial examples has led researchers to focus on enhancing the robustness of deep learning models in general, and CNNs in particular, by creating defense and detection methods to distinguish…
• Rethinking Visual Counterfactual Explanations Through Region Constraint
  16 Oct 2024 1 repository listed
  Visual counterfactual explanations (VCEs) have recently gained immense popularity as a tool for clarifying the decision-making process of image classifiers.
• Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality
  7 Oct 2024 1 repository listed Syntology ran 2 of 5 samples · 3 unverified
  These biases arise from the visual encoder and the Large Language Model (LLM) backbone, affecting the attention mechanism responsible for aligning multimodal inputs.
• CRADLE-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement
  9 Sep 2024 1 repository listed
  Predicting cellular responses to various perturbations is a critical focus in drug discovery and personalized therapeutics, with deep learning models playing a significant role in this endeavor.

Syntology lines on 9 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.