arXiv Machine Learning
Right Answer, Wrong Mechanism: Detecting Pernicious Divergence in Causal Interventions
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 25
Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining
arXiv:2606. 26050v1 Announce Type: new Abstract: Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's name ("Sue cried because"), it resolves the next pronoun to she, generalizing to held-out probes (0.
arXiv Computation and Language
Sep 25
What a Cross-Model Fixed-Point Census Can and Cannot Arbitrate About Repetition
The paper investigates neural text degeneration by measuring the fixed‑point structure of short‑window argmax maps across 17 pretrained models, using 96 random two‑token starts without prompts. It finds a stable four‑way classification that varies across model families and scales, with some models funneling to a single endpoint token while others do not, and shows that this behavior is not solely determined by training data or corpus frequency. The study demonstrates that repetition phenomena are not uniformly explained by either training data or network architecture alone, highlighting the complexity of neural text generation dynamics.
arXiv Machine Learning
Aug 5
GoT-CD: Graph-of-Thoughts Causal Discovery and the Fragility of Post-hoc Path-Specific Fairness Audits
arXiv:2608. 02877v1 Announce Type: new Abstract: Causal discovery recovers directed structure from observational data and is increasingly used in clinical settings to support mechanism reasoning and fairness audits of predictive models.
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.
arXiv Machine Learning
Sep 22
Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
arXiv:2605.01699v4 Announce Type: replace Abstract: Recent attacks show that behavioural unlearning of large language models leaves internal traces recoverable by adversarial probes. We characterise...
Hugging Face Trending Papers
Jun 24
Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining
Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's name ("Sue cried because"), it resolves the next pronoun to she, generalizing to held-out probes (0. 94 by step 925).