arXiv:2608.29352v1 Announce Type: new
Abstract: Large Language Models (LLMs) still exhibit limited capability in following complex instructions. While existing approaches often rely on preference lea...
By Runsheng Li, Kai Sun, Bin Shi, Bo Dong
arXiv:2509. 23982v2 Announce Type: replace-cross Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences.
By Lucio La Cava, Andrea Tagarelli
The paper investigates how the quality of instructions used to generate response pairs affects preference learning for language models. It shows that low‑quality or ambiguous instructions limit the range of response quality, weakening preference signals, and introduces an instruction‑refinement pipeline that improves data quality without discarding examples. Experiments across models and benchmarks demonstrate that refining instructions leads to better alignment and complements other data‑improvement methods.
By Seohyeong Lee, Hwaran Lee, Buru Chang
arXiv:2606. 16276v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, alignment is no longer governed by a single universal notion of safety or helpfulness, but instead by provider- or application-specific model specifications.
By Wenjie Wang, Yue Huang, Zhengqing Yuan, Han Bao, Shiyi Du, Yuchen Ma, Yue Zhao, Yanfang Ye, Xiangliang Zhang
arXiv:2602. 02898v3 Announce Type: replace Abstract: Language model benchmarks are pervasive and computationally-efficient proxies for real-world performance.
By Marco Gutierrez, Xinyi Leng, Hannah Cyberey, Jonathan Richard Schwarz, Ahmed Alaa, Thomas Hartvigsen
arXiv:2607. 20470v1 Announce Type: new Abstract: Enhancing the task-specific capabilities of Large Language Models (LLMs) primarily requires substantial instruction-tuning datasets.
By Jiacheng Wang, Weiyan Zhang, Guangya Yu