English
Related papers

Related papers: Spectrum Tuning: Post-Training for Distributional …

200 papers

Reinforcement learning (RL) post-training is a critical stage in modern language model development, playing a key role in improving alignment and reasoning ability. However, several phenomena remain poorly understood, including the…

Machine Learning · Computer Science 2026-01-09 Akiyoshi Tomihari

Curriculum learning-organizing training data from easy to hard-has improved efficiency across machine learning domains, yet remains underexplored for language model pretraining. We present the first systematic investigation of curriculum…

Computation and Language · Computer Science 2026-01-29 Yang Zhang , Amr Mohamed , Hadi Abdine , Guokan Shang , Michalis Vazirgiannis

Large language models (LLMs) are increasingly used for decision-making tasks under uncertainty; however, their risk profiles and how they are influenced by prompting and alignment methods remain underexplored. Existing studies have…

Artificial Intelligence · Computer Science 2025-10-08 Yikai Wang , Xiaocheng Li , Guanting Chen

As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during instruction tuning of a…

Computation and Language · Computer Science 2024-05-22 Uri Shaham , Jonathan Herzig , Roee Aharoni , Idan Szpektor , Reut Tsarfaty , Matan Eyal

Instruction tuning enhances large language models (LLMs) to follow human instructions across diverse tasks, relying on high-quality datasets to guide behavior. However, these datasets, whether manually curated or synthetically generated,…

Multilingual language models often perform unevenly across different languages due to limited generalization capabilities for some languages. This issue is significant because of the growing interest in making universal language models that…

Computation and Language · Computer Science 2024-10-11 Gürkan Soykan , Gözde Gül Şahin

Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods, offensive comments, personally identifiable information, low-quality or buggy code, and…

Computation and Language · Computer Science 2023-06-16 Tomasz Korbak , Kejian Shi , Angelica Chen , Rasika Bhalerao , Christopher L. Buckley , Jason Phang , Samuel R. Bowman , Ethan Perez

The Superficial Alignment Hypothesis posits that almost all of a language model's abilities and knowledge are learned during pre-training, while post-training is about giving a model the right style and format. We re-examine these claims by…

Computation and Language · Computer Science 2024-10-08 Mohit Raghavendra , Vaskar Nath , Sean Hendryx

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…

Computation and Language · Computer Science 2025-06-27 Zhengyan Shi

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

Machine Learning · Computer Science 2025-05-13 Xiaotian Lin , Yanlin Qi , Yizhang Zhu , Themis Palpanas , Chengliang Chai , Nan Tang , Yuyu Luo

Large Language Models (LLMs) for public use require continuous pre-training to remain up-to-date with the latest data. The models also need to be fine-tuned with specific instructions to maintain their ability to follow instructions…

Computation and Language · Computer Science 2024-10-15 Ishan Jindal , Chandana Badrinath , Pranjal Bharti , Lakkidi Vinay , Sachin Dev Sharma

Instruction tuning is vital for aligning large language models (LLMs) with human intent, but current methods typically rely on costly human-annotated seed data or powerful external teacher models. While instruction back-translation…

Computation and Language · Computer Science 2025-08-25 Zhanming Shen , Hao Chen , Yulei Tang , Shaolin Zhu , Wentao Ye , Xiaomeng Hu , Haobo Wang , Gang Chen , Junbo Zhao

Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better…

Computation and Language · Computer Science 2026-03-02 Constanza Fierro , Fabien Roger

We tackle the question of how to scale more efficiently across the many, ever-growing stages of current LLM training pipelines. Our guiding intuition stems from the fact that the dynamics of later stages of the pipeline, e.g. post-training,…

How can we train models whose post-trained capabilities survive subsequent fine-tuning? Rather than focusing on downstream interventions to mitigate forgetting of upstream capabilities, we study how upstream training choices - that is, the…

Machine Learning · Computer Science 2026-05-14 Lawrence Feng , Gaurav R. Ghosal , Jacob Mitchell Springer , Ziqian Zhong , Aditi Raghunathan

Foundation models, such as large language models (LLMs), are powerful but often require customization before deployment to satisfy practical constraints such as safety, privacy, and task-specific requirements, leading to "constrained"…

The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…

Computation and Language · Computer Science 2025-04-15 Alessandro Stolfo , Vidhisha Balachandran , Safoora Yousefi , Eric Horvitz , Besmira Nushi

Speech LLM post-training increasingly relies on efficient cross-modal alignment and robust low-resource adaptation, yet collecting large-scale audio-text pairs remains costly. Text-only alignment methods such as TASU reduce this burden by…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-10 Jing Peng , Chenghao Wang , Yi Yang , Lirong Qian , Junjie Li , Yu Xi , Shuai Wang , Kai Yu

Pretrained language models (PTLMs) are typically learned over a large, static corpus and further fine-tuned for various downstream tasks. However, when deployed in the real world, a PTLM-based model must deal with data distributions that…

Computation and Language · Computer Science 2022-07-20 Xisen Jin , Dejiao Zhang , Henghui Zhu , Wei Xiao , Shang-Wen Li , Xiaokai Wei , Andrew Arnold , Xiang Ren

Training large, general-purpose language models poses significant challenges. The growing availability of specialized expert models, fine-tuned from pretrained models for specific tasks or domains, offers a promising alternative. Leveraging…

Computation and Language · Computer Science 2025-08-19 William Fleshman , Benjamin Van Durme