counterfactual

The paper presents C3T, a thread-structured temporal model for predicting sentiment shifts in social media conversation trees using counterfactual causal reasoning, and introduces the CaSiRe dataset for causal sentiment reasoning.

Introduces DECAF, a method that decomposes perturbation responses into evidence, contradiction, and fragility components, improving interpretability over raw response magnitude and achieving strong results across vision benchmarks.

This paper introduces TKFQA, a counterfactual benchmark of 10,130 QA pairs over tables, texts, and knowledge graphs for evaluating LLM factuality consistency and order-robust reasoning, and proposes ORLF, a training framework that improves reasoning-chain accuracy and reduces input-order sensitivity.

This paper introduces Counterfactual Evidence Disentanglement (CED), a training-time method that makes vision-language models rely on concrete image evidence rather than language priors or shortcuts, improving visual reasoning grounding across benchmarks.

Introduces C3PO, a benchmark of 3,404 samples for evaluating cross-modal composition and counterfactual reasoning in multimodal LLMs. It finds modality dominance causes most failures, with even the best model (Gemini-3.1-Pro) far below human accuracy.

Introduces CARGO-VL, a group-relative optimization framework for vision-language models that improves handling of conflicting image-text evidence and unsupported-answer avoidance via counterfactual consistency and risk-constrained control, along with the XMC conflict training resource.

DoTime is a synthetic benchmark generator for interventional and counterfactual time series, providing scalable TSCM-based data generation with exact ground truth, released as a PyPI package with evaluation suites. It enables training and benchmarking causal foundation models on non-observational time series data.

Introduces Visual Attribution Distillation (VAD), a counterfactual target-reconstruction method for multimodal on-policy distillation that estimates the visually-attributable part of teacher corrections. Outperforms existing approaches across fine-grained visual benchmarks at 4B and 9B scales.

This paper proposes Counterfactual Sensitivity Credit Reallocation (CSCR), a simple extension of GRPO that reduces credit for highly sensitive tokens and renormalizes token-level advantages for long-CoT mathematical reasoning. It consistently outperforms GRPO baselines, while also revealing that privileged token-shift directions are unreliable and mostly reflect counterfactual sensitivity rather than learning value.

TokenMem injects knowledge into frozen LLMs via a dedicated cross-attention channel, training a thin gating adapter through two-phase curriculum to improve knowledge compliance under counterfactual knowledge, achieving 69-70% KC compared to 20-52% for vanilla RAG.

Introduces C-VCE, a diffusion framework that builds an interpretable concept bottleneck layer into the generative model, enabling human-guided visual counterfactual explanations without relying on external noise-robust classifiers.

This paper introduces a method for ensuring LLMs report their true beliefs by using counterfactual report coordinates that resist pressure but remain responsive to genuine evidence. The approach achieves high performance on a benchmark, demonstrating a causal certificate for internal incentive compatibility.

Proposes Counterfactual Residual Data Augmentation (CRDA) for tabular regression, leveraging residual invariance under feature perturbations to generate realistic training samples, achieving significant MSE reduction on benchmarks.

This paper uses a Transformer-based model on MLB Statcast data to counterfactually optimize baseball pitch sequences, finding that optimizing both final and setup pitches can improve season-level statistics like K/9 by over 1.0.

This paper proposes a definition of good explanations based on counterfactuals and prior beliefs, and discusses the inherent difficulties in explaining LLM outputs under this definition.

The paper identifies a failure mode where predictors collapse to a point on unidentified counterfactual couplings and proposes a framework using a positive semidefinite coupling kernel to bound counterfactuals, showing that prediction cannot represent uncertainty over cross-world couplings and that enforcing kernel constraints yields tractable bounds.

Introduces CICL, a decision-aware context layer that selects and compresses evidence for tool-using LLM agents by treating context as a decision-time intervention, using counterfactual-inspired scoring and typed memory cards under a token budget. Experiments on SWE-bench and RepoBench show concrete gains in retrieval accuracy and action criticality.

This paper introduces the Causal Sensitivity Score (CSS), an interventional metric that evaluates whether clinical LLMs and agents appropriately update their recommendations when patient inputs change along clinically meaningful dimensions. It reveals hidden capability profiles not captured by standard coverage-based metrics, exposing safety blind spots and structural responsiveness deficits.

COFT is a training-free decoding method that applies token-level fairness control and conformal calibration to reduce bias in chain-of-thought reasoning of large language models, achieving 30-55% bias reduction with minimal computational overhead.

Introduces CAFE, a benchmark for evaluating whether promptable segmentation models truly understand concepts by using counterfactual attribute manipulation, revealing that accurate mask prediction does not guarantee faithful semantic grounding.