arXiv AI
A helps B while B hurts A: directed transfer in instruction-tuning mixture
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 14
Length Penalties Make Chain-of-Thought Less Monitorable
arXiv:2607. 09786v1 Announce Type: new Abstract: Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer.
arXiv AI
Sep 15
Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models
The paper introduces Drift-Constrained Optimization (DCO), a framework that treats behavioral drift during fine‑tuning of instruction models as a bounded constraint rather than an uncontrolled side effect. By defining a drift budget, the authors reformulate fine‑tuning as a direction‑selection problem, showing that choosing different update directions can qualitatively change outcomes. Experiments on Qwen3 models demonstrate that carefully selected directions improve scientific reasoning and multilingual translation while preserving reasoning capabilities and general performance.
arXiv Machine Learning
Jul 27
Learning What Matters: Supervising Sparse Attention Routing with Causal Evidence Sets
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.
arXiv AI
Jun 2
ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks
arXiv:2606. 01080v1 Announce Type: cross Abstract: Large language models often improve on difficult tasks by spending inference-time compute on a reasoning trace before producing the final answer.
arXiv Machine Learning
Jul 30
Learning What Matters: Supervising Global Context Pruning with Causal Evidence Sets
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 Machine Learning
Aug 19
Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See
The paper evaluates how three large mixture‑of‑experts models (Alibaba, OpenAI, NVIDIA) can be fine‑tuned to reason in a low‑resource language, specifically Greek. Accuracy metrics show little change, but the authors uncover significant qualitative improvements: after supervised fine‑tuning, models reason in Greek on ~98% of items, with better grammaticality and retained general ability. Reinforcement learning with pre‑registered rewards further eliminates reasoning‑channel leaks and format skips, while the Greek‑reasoning habit remains robust to an accuracy‑only gradient.