arXiv:2512. 04144v2 Announce Type: replace Abstract: Targeted interventions on language models, such as unlearning or model editing, aim to modify specific information, but their effects often propagate to related, unintended areas (e.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
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.
arXiv:2607. 22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality.
arXiv:2606. 08036v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in academic research workflows, but scholarly tasks require high factual precision and therefore expose a key weakness: overconfidence.
arXiv:2606. 19625v1 Announce Type: 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.
arXiv:2607. 20433v1 Announce Type: cross Abstract: While language models remain frozen at their training state, the world evolves continuously.
arXiv:2608. 09209v1 Announce Type: cross Abstract: Neural language models trained on large crowdsourced corpora frequently exploit spurious surface patterns tied to target labels without true linguistic or causal relevance, boosting benchmark performance while failing on adversarial or out-of-distribution inputs.