arXiv AI

CAS: A Causal Attribution Score for Local and Global Explainable Artificial Intelligence

arXiv:2608. 12555v1 Announce Type: new Abstract: Predictive explanation methods attribute a model output; they do not, by themselves, attribute an intervention effect on the real-world outcome.

arXiv Machine Learning

Jun 10

From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts Models

arXiv:2606. 10703v1 Announce Type: new Abstract: Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of targeted interventions on specific computations; in Pearl's terms, they treat rung-1 associational evidence as if it supported rung-2 interventional conclusions, a move whose validity is rarely tested.

By Leonard Engmann, Christian Medeiros Adriano, Holger Giese

efficiency safety

arXiv Machine Learning

Aug 3

Evidence-Type Competition: When Can Interventional Data Teach Language Models Causal Direction?

arXiv:2607. 29484v1 Announce Type: cross Abstract: Interventional data is widely regarded as the gold standard for teaching models causal reasoning.

By Xining Xun

llms robotics

arXiv AI

Jun 9

Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures

arXiv:2606. 08275v1 Announce Type: cross Abstract: 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.

By Jaineet Shah

llms agents benchmarks

arXiv Machine Learning

Aug 4

Capability Provenance in Language Models: A Case Study in Social Reasoning

arXiv:2606. 19625v2 Announce Type: replace-cross Abstract: We use training-data attribution as an interpretable tool for capability discovery, mapping which regions of the pretraining corpus support social-reasoning versus STEM-reasoning in OLMo3-7B.

By Glenn Matlin, Chandreyi Chakraborty, Saehee Eom, Mika Okamoto, Rayan Castilla, Louis Jaburi, Alvin Deng, Taywon Min, Lucia Quirke, Stella Biderman, Mark Riedl

llms benchmarks

arXiv Machine Learning

Jun 26

Cross-Head Attention Uplift Network with Inverse Propensity Score under Unobserved Confounding

arXiv:2606. 27114v1 Announce Type: new Abstract: Uplift modeling, crucial for estimating individual treatment effects (ITE), faces dual challenges: flexibly leveraging inter-group similarity to enhance discriminative power and debiasing under unobserved confounding scenarios.

By Haoran Zhang, Chuanpu Li, Yuxin Fu, Bin Tong, Guan Wang, Bo Zheng, Feng Zhou

rag benchmarks safety

arXiv Machine Learning

Jul 14

Representation Learning for Semiparametric Causal Mediation Analysis under No Essential Heterogeneity

arXiv:2607. 10540v1 Announce Type: cross Abstract: We propose a two-stage estimator for structural mediation parameters that combines deep representation learning with G-estimation under the "no essential heterogeneity" (NEH) assumption.

By Roberto Faleh, Sofia Morelli, Holger Brandt

safety

arXiv AI

Jun 16

Not All Skills Help: Measuring and Repairing Agent Knowledge

arXiv:2606. 15390v1 Announce Type: cross Abstract: LLM agents can improve without weight updates by accumulating natural-language skills from experience, but current systems entrust every decision about which skills to keep and how to apply them to LLM judgment alone.

By Yixuan Wang, Yiyang Zhou, Yiming Liang, Congyu Zhang, Fuxiao Liu, Jiawei Zhou, Huaxiu Yao

llms agents benchmarks

arXiv Machine Learning

Jun 5

A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR

arXiv:2606. 05932v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) improves reasoning even when the reward signal is spurious -- assigning credit to the group-plurality answer rather than a ground-truth verifier.

By Yuze Gao

reinforcement-learning safety

arXiv Machine Learning

Jul 27

LLM-Extracted Covariates for Clinical Causal Inference: Rethinking Integration Strategies

arXiv:2604. 16763v3 Announce Type: replace Abstract: Causal inference from electronic health records (EHR) is fundamentally limited by unmeasured confounding: critical clinical states such as frailty, goals of care, and mental status are documented in free-text notes but absent from structured data.

By Lei Liu, Jialin Chen, Kathy Macropol

llms nlp safety

arXiv AI

Jul 17

Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities

arXiv:2604. 23904v3 Announce Type: replace-cross Abstract: Synthetic tabular data are often evaluated by distributional similarity, privacy distance, or train-on-synthetic-test-on-real predictive performance, but these criteria do not ensure validity for causal inference.

By Yichen Xu

llms diffusion benchmarks safety

arXiv Machine Learning

Jun 5

Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability

arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.

By Yash Aggarwal, Atmika Gorti, Vinija Jain, Aman Chadha, Krishnaprasad Thirunarayan, Manas Gaur

llms efficiency safety

arXiv Machine Learning

Jul 10

Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability

arXiv:2607. 08349v1 Announce Type: new Abstract: Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components, or comparing a compressed model to the original one.

By Amir Asiaee

llms safety

Related stories