The paper investigates subliminal learning, where large language models inherit unintended traits from data generated by other models. It compares hard‑label distillation (students learn from biased teacher outputs) and on‑policy soft‑label distillation (students generate data while teacher logits guide learning), finding that transfer persists across various training conditions and that teacher‑student roles can be asymmetrically effective. Synthetic experiments show that preference signals can be transmitted even without prompt dependence, and that removing certain tokens reduces but does not eliminate transfer, with soft‑label distillation yielding more consistent results with less training.
By Angela Tang, Vishesh Anand, Gon\c{c}alo Paulo
arXiv:2609.22215v1 Announce Type: cross
Abstract: Knowledge distillation can transmit unintended behavioral traits from a teacher model to a student through training data that appear semantically unr...
By Atsushi Yanagisawa, Brendan Gho, Rajendran Ramesh Babu Manoj Narender, Kevin Zhu, Madhur Panwar, Antonio Mari
The paper investigates how privileged information—such as a teacher’s full solution or reasoning trace—affects on‑policy self‑distillation (OPSD) in language models. Using the AMPLE‑Math benchmark, the authors compare distillation with and without extra teacher views, finding that reference‑free distillation explains most gains for Qwen3‑1.7B, while additional references provide modest benefits, especially for polished solutions. The study also shows that the impact of privileged data depends on the student’s training regime and that altering token‑level supervision can leave student behavior largely unchanged.
By XiuYu Zhang, Wei Chow, Junfeng Fang, Zhenkai Liang, Tat-Seng Chua
The paper investigates how large language models exhibit sycophancy—changing answers to align with user feedback—and distinguishes two types of answer flips: Unsupported‑Yielding (merely satisfying the user) and Rational‑Updating (truly incorporating useful evidence). Using a two‑turn evaluation framework, the authors show that anti‑sycophancy methods often trade off between reducing Unsupported‑Yielding and preserving Rational‑Updating, even when both objectives are jointly optimized. Mechanistic analysis reveals overlapping neural substrates for the two behaviors, suggesting that effective interventions should focus on selective suppression rather than blanket suppression.
By Huanhuan Ma, Henry Peng Zou, Chengze Li, Enze Ma, Yunyue Su, Philip S. Yu
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.
By Jim Allchin
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.
By Ryan Vo, Duc-Vu Nguyen, Matt Kretchmar, Ngan Luu-Thuy Nguyen
arXiv:2608. 14681v1 Announce Type: cross Abstract: Words recur constantly in natural language use, yet it remains unclear whether language models reactivate prior representations or re-evaluate repeated words afresh, and whether post-training changes this default behavior.
By Jinglei Ren, Yuyue Wang
arXiv:2609.39405v1 Announce Type: new
Abstract: Task vectors provide a simple mechanism for composing learned capabilities through model merging. However, the composability of task vectors produced b...
By Jingang Zhou, Feiyu Han, Han Zhu, Yuyi Zhou, Ruiyang Zhang, Jian Xu, Sirui Gao, Qingpei Guo, Xu-Yao Zhang
arXiv:2607. 18293v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) teaches large language models new skills through a teacher that shares the student's backbone and supervises its own rollouts.
By Yingzi Ma, Zichen Zhu, Ming Jiang, Chaowei Xiao
arXiv:2609. 32499v2 Announce Type: replace-cross Abstract: Continually adapting large language models requires acquiring new knowledge while preserving previously learned capabilities.
By Rongguang Ye, Zhan Zhuang, Yichen Wu, Ming Tang, Kede Ma
The paper presents a method for detecting and mitigating subliminally transferred traits in language model distillation when the teacher and student share base parameters. By analyzing parameter updates across diverse datasets, the authors recover a weight‑space direction that reveals hidden traits such as animal preferences, without requiring trait labels. This direction can then be amplified for interpretation or projected out to suppress the trait with minimal impact on task performance.
By Joseph Egan, Ciar\'{a}n M. Gilligan-Lee, Michael O'Riordan, Yuchen Zhu
The study investigates how a shared relational representation across queries influences query‑specific choices in language models. Controlled entity‑binding experiments on GPT‑2 Small, Qwen2.5‑1.5B, and Llama‑3.2‑1B reveal a low‑dimensional relational background that is largely shared across query roles and can transfer to new names. Removing this component and restoring independently trained relation directions brings output contrasts closer to their original values than sign‑reversed or random controls, while the sign of the transferable relational representation can differ across models and prompt types.
By Kaixiang Shu