The study investigates whether restricting a module’s access to information—through evidence masking—enhances a system’s ability to learn compositional tasks. In a preregistered experiment with sixty‑four‑cell systems built on a frozen language‑model backbone, researchers varied evidence masking, ownership markers, and filler replacement across multiple initialization clusters and data orders. Results showed that when markers were available, masking significantly improved accuracy on held‑out two‑ and three‑operation compositions, with all tested pairs meeting performance thresholds and the preregistered behavioral criterion satisfied. The study also explored packet interventions and found predicted intermediate‑value changes, though mediation was not conclusively established. "whyItMatters":"The findings demonstrate a substantial performance benefit from evidence masking in compositional generalization tasks, offering a promising direction for designing more effective learning systems."
arXiv:2608. 20054v1 Announce Type: new Abstract: Multi-module systems often expose every module to the full input.
arXiv:2608.20054v3 Announce Type: replace Abstract: Multi-module neural systems often expose every module to the full input. We test whether a slot-selective evidence-masking regime -- restricting ea...
The study investigates whether independently trained language‑model societies share a common packet language and how inherited interface states affect learning. A comprehensive audit of 30 pairwise interactions among six restricted societies shows that only one pair is fully interoperable, another is partially compatible, and the remaining 26 pairs fail across all alignment levels. Further experiments reveal that a globally trained communication interface can act as a severe negative‑transfer prior, but inherited interfaces never outperform fresh‑interface controls by the preregistered margin.
The study investigates whether independently trained language‑model societies share a common packet language and how inherited interface states affect learning. A comprehensive audit of 30 pairwise interactions among six restricted societies shows that most cross‑initialization pairs fail to interoperate, with only one pair achieving full bidirectional compatibility. Further experiments reveal that reinitializing only the packet reader, writer, and mouth dramatically improves accuracy, while inherited interfaces never outperform fresh ones by the preregistered margin.
arXiv:2606. 05976v1 Announce Type: new Abstract: Recent work shows that LLM agents struggle to correct errors in their own reasoning traces yet show markedly higher correction rates when identical claims appear under external sources.
arXiv:2606. 05976v2 Announce Type: replace Abstract: Recent works show that LLM agents struggle to correct errors in their own reasoning traces, despite their ability to correct errors from external sources.
The paper questions whether large language models (LLMs) truly introspect by critiquing recent studies that claim they can detect and report their internal states. It proposes two necessary conditions for genuine introspection: privileged access to internal representations and second‑order computation that distinguishes from first‑order task performance. Re‑examining two existing paradigms, the authors find that apparent introspective abilities can be explained by input‑based classifiers or generic anomaly detection, concluding that current evidence does not support metacognitive monitoring in LLMs.
arXiv:2609.22090v1 Announce Type: new Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Ps...
BodhiPromptShield is a policy‑aware mediation layer for LLM agent pipelines that detects sensitive text spans before they propagate, replacing them with typed placeholders, semantic abstractions, or secure tokens and restoring them only at authorized execution boundaries. In evaluations on AI4Privacy, PrivacyLens, and AgentDojo datasets, the system reduces identifier exposure to 7.4% and 1.8% respectively, and limits exact identifier leakage in final actions to 2.1–3.1%. While mediation preserves factual content according to automated metrics, human annotations show a significant drop in inferability from 100% to 24–53%, indicating the need for human validation of semantic‑leakage measures.
arXiv:2607. 18639v1 Announce Type: new Abstract: Safety interventions on dual-use knowledge typically choose between destroying hazardous content (e.
The study investigates whether open‑weight language models can introspect on their own internal computations. Using the Open‑Weight Masked Introspection (OWMI) framework, researchers intervened on various internal components of eight models and asked them to report whether changes had occurred. Across 78,000 measurements, none of the models reliably distinguished real interventions from sham ones, with AUROC values essentially at chance. Why It Matters: The findings suggest that current open‑weight models lack the ability to audit their own internal states, highlighting a limitation for oversight that relies on a model’s self‑reporting.
arXiv:2606. 12747v1 Announce Type: new Abstract: Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model outputs.