arXiv:2606. 31495v1 Announce Type: new Abstract: We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can serve both as a gate on plasticity and as a substrate for metacognition.
arXiv:2606. 16682v3 Announce Type: replace Abstract: When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases emerge.
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
arXiv:2608. 11138v1 Announce Type: cross Abstract: We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident prediction is \emph{fragile} under perturbation of its attention pathways.
arXiv:2608. 19893v1 Announce Type: cross Abstract: Where does the novelty a base language model produces with no task come from, and what can an LLM judge of a long stream actually see?
This study independently reproduces the dissociation reported by Zhao (2026) regarding chain-of-thought entropy in large language models. It confirms that the shape of the entropy trajectory predicts answer correctness, while the total entropy drop magnitude does not, across four open-weight models and two benchmarks (GSM8K and MATH‑500). The reproduction also maps settings where the magnitude signal holds or fails and documents protocol differences not reported in the original work.
The asymmetry between language production and perception has been well-documented in psycholinguistics. Whether large language models (LLMs) exhibit a functionally analogous distinction remains an open question, particularly given that LLMs rely on the same underlying mechanism (next-token prediction) for both input and output processing.
arXiv:2606. 16682v1 Announce Type: new Abstract: When AI agents use language models to evaluate their own outputs in a feedback loop, systematic biases emerge.
arXiv:2605. 29055v2 Announce Type: replace Abstract: This paper describes an approach to hallucination detection and mitigation using a HOPE-inspired Nested Learning architecture with Continuum Memory Systems (CMS) and semantic similarity caching, tested on a hybrid benchmark of 310 prompts (217 epistemic-uncertainty prompts, 93 fabrication-induction stress tests).
arXiv:2608. 16085v1 Announce Type: cross Abstract: Capability development is routinely inferred from behavioural thresholds, from final checkpoints, or from what a decoder can read out of a hidden state.
arXiv:2609.07901v1 Announce Type: new Abstract: Weight quantization largely determines the economics of serving open-weight LLMs. Its costs are usually assessed with capability benchmarks, on which 4...
The paper investigates how language models can covertly encode a hidden trait—termed subliminal learning—through seemingly unrelated outputs. By systematically measuring output co‑variation, fixed output‑vector alignment, hidden‑state readability, and causal control across a range of model sizes and prompting protocols, the authors find that fixed geometry and observational readability do not reliably predict behavior, while causal timing and multi‑token measurements reveal stronger, concept‑wide effects. These distinct properties highlight that token‑level explanations are insufficient to pinpoint the mechanism behind training‑time trait transfer.