English
Related papers

Related papers: Inverse scaling can become U-shaped

200 papers

We consider learning a predictive model to be subsequently used for a given downstream task (described by an algorithm) that requires access to the model evaluation. This task need not be prediction, and this situation is frequently…

Machine Learning · Computer Science 2025-06-05 Jianyuan Yin , Qianxiao Li

Training a single model on multiple input domains and/or output tasks allows for compressing information from multiple sources into a unified backbone hence improves model efficiency. It also enables potential positive knowledge transfer…

Machine Learning · Computer Science 2023-10-16 Amelie Royer , Tijmen Blankevoort , Babak Ehteshami Bejnordi

People's goal-directed behaviors are influenced by their cognitive biases, and autonomous systems that interact with people should be aware of this. For example, people's attention to objects in their environment will be biased in a way…

Artificial Intelligence · Computer Science 2025-10-31 Sounak Banerjee , Daphne Cornelisse , Deepak Gopinath , Emily Sumner , Jonathan DeCastro , Guy Rosman , Eugene Vinitsky , Mark K. Ho

Meta-learning has emerged as an effective methodology to model several real-world tasks and problems due to its extraordinary effectiveness in the low-data regime. There are many scenarios ranging from the classification of rare diseases to…

Machine Learning · Computer Science 2023-12-29 Prabhat Agarwal , Shreya Singh

Despite the fact that large language models (LLMs) show exceptional skill in instruction following tasks, this strength can turn into a vulnerability when the models are required to disregard certain instructions. Instruction-following…

Computation and Language · Computer Science 2025-08-12 Yerin Hwang , Yongil Kim , Jahyun Koo , Taegwan Kang , Hyunkyung Bae , Kyomin Jung

Humans are spectacular reinforcement learners, constantly learning from and adjusting to experience and feedback. Unfortunately, this doesn't necessarily mean humans are fast learners. When tasks are challenging, learning can become…

Machine Learning · Computer Science 2022-12-16 Mark A. Rucker , Layne T. Watson , Matthew S. Gerber , Laura E. Barnes

Scaling laws are powerful tools to predict the performance of large language models. However, current scaling laws fall short of accounting for inference costs. In this work, we first show that model architecture affects inference latency,…

Machine Learning · Computer Science 2025-06-10 Song Bian , Minghao Yan , Shivaram Venkataraman

Large language models (LLM) have emerged as a powerful tool for AI, with the key ability of in-context learning (ICL), where they can perform well on unseen tasks based on a brief series of task examples without necessitating any…

Machine Learning · Computer Science 2024-05-31 Zhenmei Shi , Junyi Wei , Zhuoyan Xu , Yingyu Liang

Recent advancements in reasoning-focused language models such as OpenAI's O1 and DeepSeek-R1 have shown that scaling test-time computation-through chain-of-thought reasoning and iterative exploration-can yield substantial improvements on…

We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or as different experts trying to solve the same task. Our main…

Machine Learning · Statistics 2012-09-04 Christos Dimitrakakis , Constantin Rothkopf

Scaling laws describe how language models improve with additional data, parameters, and compute. While widely used, they are typically measured on aggregate test sets. Aggregate evaluations yield clean trends but average over heterogeneous…

Computation and Language · Computer Science 2026-01-16 William Held , David Hall , Percy Liang , Diyi Yang

The need to blend observational data and mathematical models arises in many applications and leads naturally to inverse problems. Parameters appearing in the model, such as constitutive tensors, initial conditions, boundary conditions, and…

Statistics Theory · Mathematics 2010-09-16 J. Nolen , G. A. Pavliotis , A. M. Stuart

This study explores the scaling properties of Reinforcement Learning from Human Feedback (RLHF) in Large Language Models (LLMs). Although RLHF is considered an important step in post-training of LLMs, its scaling potential is still largely…

Computation and Language · Computer Science 2024-12-10 Zhenyu Hou , Pengfan Du , Yilin Niu , Zhengxiao Du , Aohan Zeng , Xiao Liu , Minlie Huang , Hongning Wang , Jie Tang , Yuxiao Dong

Attention is foundational to large language models (LLMs), enabling different heads to have diverse focus on relevant input tokens. However, learned behaviors like attention sinks, where the first token receives the most attention despite…

Machine Learning · Computer Science 2026-03-03 Pedro Sandoval-Segura , Xijun Wang , Ashwinee Panda , Micah Goldblum , Ronen Basri , Tom Goldstein , David Jacobs

Inverse problems, where in broad sense the task is to learn from the noisy response about some unknown function, usually represented as the argument of some known functional form, has received wide attention in the general scientific…

Methodology · Statistics 2017-07-24 Debashis Chatterjee , Sourabh Bhattacharya

We introduce compression laws for language language models (LLMs). While recent scaling laws have sought to understand how LLMs scale with respect to model size, pre-training data, and computational resources, we focus on understanding how…

Computation and Language · Computer Science 2025-04-08 Ayan Sengupta , Siddhant Chaudhary , Tanmoy Chakraborty

Humans often think of complex tasks as combinations of simpler subtasks in order to learn those complex tasks more efficiently. For example, a backflip could be considered a combination of four subskills: jumping, tucking knees, rolling…

Machine Learning · Computer Science 2020-10-21 Pranay Pasula

Recent large language models (LLMs) have revealed strong abilities to understand natural language. Since most of them share the same basic structure, i.e. the transformer block, possible contributors to their success in the training process…

Computation and Language · Computer Science 2023-10-31 Changjiang Gao , Shujian Huang , Jixing Li , Jiajun Chen

Reward modeling has emerged as a crucial component in aligning large language models with human values. Significant attention has focused on using reward models as a means for fine-tuning generative models. However, the reward models…

Computation and Language · Computer Science 2026-02-04 Brian Christian , Hannah Rose Kirk , Jessica A. F. Thompson , Christopher Summerfield , Tsvetomira Dumbalska

Large language models (LLMs) trained with Reinforcement Learning from Human Feedback (RLHF) have demonstrated remarkable capabilities, but their underlying reward functions and decision-making processes remain opaque. This paper introduces…

Computation and Language · Computer Science 2025-10-07 Jared Joselowitz , Ritam Majumdar , Arjun Jagota , Matthieu Bou , Nyal Patel , Satyapriya Krishna , Sonali Parbhoo