← Back to all news
arXiv Machine Learning

Slow Decay and Silenced Expression: Iterated Subliminal Trait Transfer in Language-Model Lineages

The study investigates whether a subliminal trait can persist across multiple generations of language‑model lineages. Three copies of Qwen2.5‑7B‑Instruct were trained for ten iterations, and the trait’s expression was measured via a keyword screen and an activation probe. Results show the trait remains detectable in all generations, though its behavioral expression diminishes, and it can exist internally without being overtly expressed when the system prompt is removed.

Related stories

arXiv Machine Learning
Sep 18

Subliminal Prompting Beyond Static Geometry: Causal Depth and Multi-Token Confounds

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.

By Barath Velmurugan
llms
More like this →
arXiv AI
6d ago

Post-Training Leaves Behavioral Shadows on Unrelated Decisions

The paper demonstrates that language models can acquire new capabilities from post‑training data even when the training text is unrelated to the target task. Using a method called Active Taskless Distillation (ATD), the authors show that a single word from a teacher model can transfer knowledge to a student model without any target‑task examples or teacher logits. Experiments on Qwen2.5-1.5B reveal significant performance gains on HumanEval+ and improvements in scientific knowledge, commonsense reasoning, and reading comprehension across various model families.

By Ziyang Zhang, Yubin Jing, Yuanhao Zeng, Yuyao Li, Haofan Wang, Yichen Gong
llmsefficiencybenchmarks
More like this →
arXiv Machine Learning
Sep 17

No Usable Linear "Capitulation Direction" in Two Small LLMs: A Validation Protocol for Activation-Steering Claims, and a Cross-Family Behavioral Study of Sycophancy Under Pushback

The study examines how two small instruction‑tuned language models, Qwen2.5‑1.5B and Llama‑3.2‑1B, respond to user pushback on TriviaQA. When initially correct, the models flip to a wrong answer in about 42–43% of cases, with the effectiveness of different pushback styles varying by model. Attempts to decode capitulation from the pre‑response residual stream fail under a rigorous validation protocol, revealing overfitting and a measurement hazard that underestimates capitulation by 18–24 percentage points.

By Saad Aamir, Muhammad Awais Bin Adil
llms
More like this →
arXiv AI
Jun 2

When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures

arXiv:2606. 02378v1 Announce Type: cross Abstract: We track the developmental trajectory of attention-head circuit formation across three 1B-class language models spanning two architecture families (dense transformer, mixture-of-experts) and two pretraining corpora (The Pile, DCLM): Pythia 1B, OLMo 1B-0724-hf, and OLMoE 1B-7B-0924.

By Yongzhong Xu
llmssafety
More like this →