arXiv Machine Learning June 3, 2026 By Zirui Yan, Dennis Wei, Dmitriy A. Katz, Prasanna Sattigeri, Ali Tajer

Multi-component Causal Tracing in Large Language Models

Read the original on arXiv Machine Learning →

arXiv:2606. 03085v1 Announce Type: new Abstract: Causal tracing systematically intervenes on a large language model's (LLM's) internal representations to uncover and quantify the causal pathways linking specific inputs or computations to specific metrics of interest, quantifying the LLM's behavior.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 9

TempoBench: Evaluating Temporal Causal Reasoning in Large Language Models

arXiv:2510. 27544v2 Announce Type: replace Abstract: Temporal reasoning involves understanding how systems evolve over time through input-driven state transitions.

By Nikolaus Holzer, William Fishell, Baishakhi Ray, Mark Santolucito

llms fine-tuning benchmarks

arXiv AI

Jul 2

CausalMix: Data Mixture as Causal Inference for Language Model Training

arXiv:2607. 01104v1 Announce Type: cross Abstract: In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance.

By Zinan Tang, Yukun Zhang, Shaomian Zheng, Zhuoshi Pan, Qizhi Pei, Dingnan Jin, Jun Zhou, Yujun Wang, Biqing Huang

llms

arXiv AI

Aug 6

Can Post-Training Transform LLMs into Causal Reasoners?

arXiv:2602. 06337v2 Announce Type: replace-cross Abstract: Causal inference is essential for decision-making but remains challenging for non-experts.

By Junqi Chen, Sirui Chen, Chaochao Lu

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 6

ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents

arXiv:2606. 06284v1 Announce Type: new Abstract: Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and token cost.

By Rahul Suresh Babu, Laxmipriya Ganesh Iyer

llms agents benchmarks

arXiv AI

Aug 3

Stem: Rethinking Causal Information Flow in Sparse Attention

arXiv:2603. 06274v2 Announce Type: replace-cross Abstract: The quadratic computational complexity of self-attention remains a fundamental bottleneck for scaling Large Language Models (LLMs) to long contexts, particularly during the pre-filling phase.

By Lin Niu, Xin Luo, Linchuan Xie, Yifu Sun, Guanghua Yu, Jianchen Zhu, S Kevin Zhou

llms efficiency

arXiv AI

Jun 29

CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching

arXiv:2602. 20094v2 Announce Type: replace Abstract: As large language models (LLMs) witness increasing deployment in complex, high-stakes decision-making scenarios, it becomes imperative to ground their reasoning in causality rather than spurious correlations.

By Yuzhe Wang, Yaochen Zhu, Jundong Li

llms benchmarks

Related stories

TempoBench: Evaluating Temporal Causal Reasoning in Large Language Models

CausalMix: Data Mixture as Causal Inference for Language Model Training

Can Post-Training Transform LLMs into Causal Reasoners?

ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents

Stem: Rethinking Causal Information Flow in Sparse Attention

CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching