arXiv:2607. 08393v1 Announce Type: new Abstract: Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning tasks.
By Lu Dai, Ziyang Rao, Yili Wang, Hanqing Wang, Hao Liu, Hui Xiong
arXiv:2602. 04843v2 Announce Type: replace Abstract: Frontier large language models increasingly solve complex tasks involving abstract concepts through extended test-time thinking.
By Dmitrii Kharlapenko, Terry Jingchen Zhang, Arth Singh, Alessandro Stolfo, Arthur Conmy, Mrinmaya Sachan, Zhijing Jin
Instruction tuning is often thought to give language models a universal ability to follow instructions, but this study shows otherwise. By probing nine tasks across three models, the authors find that general probes reveal selective, not uniform, deficits, cross‑task transfer is weak and skill‑similar, and causal ablation uncovers sparse, asymmetric dependencies. The results suggest instruction following is a coordinated use of diverse linguistic skills rather than a single shared mechanism.
By Elisabetta Rocchetti, Alfio Ferrara
arXiv:2606. 05680v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the automatic synthesis (generation) of register-transfer level (RTL) code from natural language instructions, offering a promising pathway to accelerate chip design.
By Mohammad Akyash, Nowfel Mashnoor, Kimia Azar, Hadi Kamali
The paper investigates how different prompt adaptation techniques—discrete prompt optimization, prompt tuning, and prefix tuning—affect the internal processing of dense and mixture-of-experts language models. It finds that the adaptation location determines how task information reaches the output: text prompts mainly influence response construction, input-level prompts modify content representations, and layer-wise prefixes exert direct control via attention. In MoE models, these differences also lead to distinct expert‑routing patterns, while generic representation‑level metrics fail to reliably distinguish effective adaptations from placebo effects.
By Mikhail Aleksandrov, Nail Bashirov, Maksim Ivanov, Andrew Tsukanov, Timofey Karyagin, Alexander Miasnikov, Gleb Molodtsov, Valentin Samokhin, Aleksandr Beznosikov
arXiv:2608.23497v1 Announce Type: new
Abstract: Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving wit...
By Yipeng Zhao, Qishun Yang, Shenzhe Zhu, Shu Yang, Di Wang