Counterfactual Chains
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
LLM Explainability with Counterfactual Chains and Causal Graphs
Announce Type: new Abstract: Causal graphs provide a high-level language for making mechanisms transparent. Recent work uses Large Language Models (LLMs) to recover causal graphs of external-world processes. Instead, in this paper, we use causal graphs to model LLM inference itself, providing stakeholders with a transparent view of how the model perceives and organizes high-level concepts to produce a prediction.
COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models
Announce Type: new Abstract: Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation. We present COFT (Chain of Fair Thought), a training-free decoding method that applies token-level fairness control at decode time, with distribution-free marginal validity guarantees (under exchangeability) for any frozen causal language model. COFT operates in three stages.
VeriDrive: Verifiable Counterfactual Supervision for Cost-Efficient Vision-Language Planning
arXiv:2606.07338v1 Announce Type: new Abstract: Vision-language driving models increasingly use reasoning supervision to bridge perception, prediction, and planning, but existing driving rationales are often free-form and expensive to generate with frontier models. We present VeriDrive, a framework for constructing planning-oriented, verifiable counterfactual supervision. VeriDrive converts driving reasoning into a structured Perception-Evaluation-Revision chain that grounds key objects in...
Distilling Counterfactual Reasoning from Language to Vision: Causal Graph Guided Post-Training for Video Understanding
Announce Type: replace Abstract: Vision Language Models (VLMs) have recently shown significant advancements in video understanding, especially in feature alignment, event reasoning, and instruction-following tasks. However, their capability for counterfactual reasoning, inferring alternative outcomes under hypothetical conditions, remains underexplored. This capability is essential for robust video understanding, as it requires identifying underlying causal structures and reasoning about...
Output Type Before Quality: A Standards-Derived XAI Admissibility Rubric for Autonomous-Driving Safety
Announce Type: new Abstract: Safety standards for ML-based autonomous driving specify the kind of evidence an assurance case must contain (directed cause-and-effect chains, quantified interventional effects, named root-cause variables), yet the XAI literature is organised by output type and technique family (saliency maps, feature attribution, counterfactuals, causal graphs, language traces). SHAP, the most-recommended ADS XAI method, returns a ranked feature list that no implementation...
Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya
arXiv:2604.04937v1 Announce Type: cross Abstract: Large language models produce fluent text but struggle with systematic reasoning, often hallucinating confident but unfounded claims. When Apple researchers added irrelevant context to mathematical problems, LLM performance degraded by 65% Apple Machine Learning Research, exposing brittle pattern-matching beneath apparent reasoning. This epistemic gap, the inability to ground claims in traceable evidence, limits AI reliability in domains...
Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents
arXiv:2606.05263v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves reasoning and tool use, yet long-horizon language agents still learn unsupported evidence chains, belief drift, and shortcut actions that satisfy terminal checks. Existing process rewards are mostly correlational: they reward retrieval-, reflection-, or verification-like steps without estimating whether the step contributes to final verified success under a specified intervention. We...
State commitment learning: training language models to distinguish computation from memory
arXiv:2606.05201v1 Announce Type: new Abstract: Reasoning language models do not distinguish tokens used for computation from tokens that constitute persistent state: once generated, all hidden thoughts remain in context and influence future predictions. As a result, downstream reasoning may depend on failed attempts, dead ends, and private scratch work that should not be safely relied on later. We recast this phenomenon as a new training objective, state commitment learning: training models...
From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning
new Abstract: Theory of Mind (ToM) is a must-acquire skill for modern foundation model systems to operate effectively and safely in the real world. Recent works have explored honing ToM via post-training; however, we show that such progress is confounded by a pervasive "shortcut" issue: tasks can reach up to 99% accuracy by simply exploiting spurious causal correlations, leading to a false sense of ToM. Motivated by this, we first develop a framework to systematically examine ToM datasets...
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
arXiv:2604.26283v3 Announce Type: replace Abstract: High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during image interpretation. We pinpoint a fundamental cognitive misalignment in medical VLMs caused by discrete tokenization, leading to quantization loss, long-range information dissipation, and missing case-adaptive expertise. To bridge this gap, we propose ours, a framework for latent diagnostic...