arXiv:2606. 03780v1 Announce Type: cross Abstract: Causal tracing of factual recall has been studied predominantly in dense transformer language models, where interventions localize information flow to layers or feed-forward modules.
arXiv:2607. 20426v1 Announce Type: cross Abstract: Existing LLM hallucination mitigation methods, including prompt engineering and model optimization, either hardly alter models'internal knowledge or have poor cross-domain generalization.
arXiv:2606. 10338v1 Announce Type: cross Abstract: Machine unlearning is increasingly important for large language models, yet unlearning in Mixture-of-Experts (MoE) architectures remains underexplored.
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.
arXiv:2607. 21692v2 Announce Type: replace Abstract: Sparse attention prunes a long context to the blocks a model needs, and the usual selector is distilled from a dense teacher's attention.
arXiv:2605. 09692v3 Announce Type: replace Abstract: Autonomous language agents increasingly expose traces, memories, plans and constraints, but existing evaluations rarely test whether these state variables are bound to final actions.
arXiv:2608. 17638v1 Announce Type: new Abstract: What a reasoning model writes is only a partial record of the process that produces it.
arXiv:2606. 25092v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models route each token to a few of many experts, inviting the hypothesis that experts form functional modules tied to capabilities or languages.
What a reasoning model writes is only a partial record of the process that produces it. We introduce a two-level internal readout for mixture-of-experts reasoning.
arXiv:2608. 07911v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have outgrown accelerator memory, and offloading expert weights to host memory is now standard.
arXiv:2608. 15687v1 Announce Type: new Abstract: Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure.
arXiv:2607. 26929v1 Announce Type: cross Abstract: The same diagnostic result can support or challenge one causal claim yet fail to address another when the claims concern different populations, outcomes, estimands, pathways, or identifying assumptions.
arXiv:2607. 21692v1 Announce Type: new Abstract: Sparse attention reduces the cost of long contexts by allowing each query to read only selected parts of the input.