English
Related papers

Related papers: Chunky Post-Training: Data Driven Failures of Gene…

200 papers

Past work has studied the effects of fine-tuning on large language models' (LLMs) overall performance on certain tasks. However, a quantitative and systematic method for analyzing its effect on individual outputs is still lacking. Here, we…

Computation and Language · Computer Science 2025-07-01 Felipe Nuti , Tim Franzmeyer , João Henriques

Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-training uses different objectives to shape different behaviors, we argue that unlearning…

Computation and Language · Computer Science 2026-05-27 Berk Atil , Vipul Gupta , Rebecca J. Passonneau

As language models (LMs) deliver increasing performance on a range of NLP tasks, probing classifiers have become an indispensable technique in the effort to better understand their inner workings. A typical setup involves (1) defining an…

Computation and Language · Computer Science 2024-08-01 Charles Jin , Martin Rinard

Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…

Computation and Language · Computer Science 2025-10-31 Yuto Harada , Yusuke Yamauchi , Yusuke Oda , Yohei Oseki , Yusuke Miyao , Yu Takagi

Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs), yet datasets are often treated as isolated artifacts, overlooking the systemic connections that underlie their evolution. To disentangle…

Artificial Intelligence · Computer Science 2026-04-14 Yu Li , Xiaoran Shang , Qizhi Pei , Yun Zhu , Xin Gao , Honglin Lin , Zhanping Zhong , Zhuoshi Pan , Zheng Liu , Xiaoyang Wang , Conghui He , Dahua Lin , Feng Zhao , Lijun Wu

In this paper, we study how the intrinsic nature of pre-training data contributes to the fine-tuned downstream performance. To this end, we pre-train different transformer-based masked language models on several corpora with certain…

Computation and Language · Computer Science 2020-12-23 Cheng-Han Chiang , Hung-yi Lee

In the current landscape of large language models (LLMs), the process of instruction tuning serves as an essential step. Considering the high computing power overhead, data-efficient instruction tuning was proposed to reduce the training…

Computation and Language · Computer Science 2025-01-06 Qi Zhang , Yiming Zhang , Haobo Wang , Junbo Zhao

Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In this work we systematically investigate how specific…

Computation and Language · Computer Science 2024-12-23 Joongwon Kim , Anirudh Goyal , Aston Zhang , Bo Xiong , Rui Hou , Melanie Kambadur , Dhruv Mahajan , Hannaneh Hajishirzi , Liang Tan

Scaled post-training now drives many of the largest capability gains in language models (LMs), yet its effect on pretrained knowledge remains poorly understood. Not all forgetting is equal: Forgetting one fact (e.g., a U.S. president or an…

Machine Learning · Computer Science 2025-10-21 Jackson Harmon , Andreas Hochlehnert , Matthias Bethge , Ameya Prabhu

Neural networks trained on real-world data often exhibit biases while simultaneously being vulnerable to privacy attacks aimed at extracting sensitive information. Despite extensive research on each problem individually, their intersection…

Machine Learning · Computer Science 2025-10-07 Chenxiang Zhang , Jun Pang , Sjouke Mauw

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Machine Learning · Computer Science 2026-01-01 Haoyue Bai , Yiyou Sun , Wenjie Hu , Shi Qiu , Maggie Ziyu Huan , Peiyang Song , Robert Nowak , Dawn Song

Recent research has highlighted the importance of dataset size in scaling language models. However, large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its…

Machine Learning · Computer Science 2023-10-10 Fuzhao Xue , Yao Fu , Wangchunshu Zhou , Zangwei Zheng , Yang You

The analysis of long sequence data remains challenging in many real-world applications. We propose a novel architecture, ChunkFormer, that improves the existing Transformer framework to handle the challenges while dealing with long time…

Machine Learning · Computer Science 2022-01-03 Yue Ju , Alka Isac , Yimin Nie

Neural Linear Models (NLM) are deep Bayesian models that produce predictive uncertainty by learning features from the data and then performing Bayesian linear regression over these features. Despite their popularity, few works have focused…

Machine Learning · Statistics 2021-06-25 Cooper Lorsung

In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized into sequential token representations. However, even when sufficient knowledge is…

Computation and Language · Computer Science 2026-05-27 Shanghao Li , Jinda Han , Yibo Wang , Yuanjie Zhu , Zihe Song , Langzhou He , Kenan Kamel A Alghythee , Philip S. Yu

Large Language Models (LLMs) that undergo recursive training on synthetically generated data are susceptible to model collapse, a phenomenon marked by the generation of meaningless output. Existing research has examined this issue from…

Computation and Language · Computer Science 2026-03-17 Konstantinos F. Xylogiannopoulos , Petros Xanthopoulos , Panagiotis Karampelas , Georgios A. Bakamitsos

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning as the dual problem: given a desired form of generalization,…

Machine Learning · Computer Science 2026-01-21 George Wang , Daniel Murfet

Learning correlations from data forms the foundation of today's machine learning (ML) and artificial intelligence research. While contemporary methods enable the automatic discovery of complex patterns, they are prone to failure when…

Machine Learning · Computer Science 2026-05-05 Samuel J. Bell , Skyler Wang

Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies concentrate on fully pre-trained LLMs to better understand and improve LLMs' trustworthiness. In this paper, to reveal the untapped potential of…

Computation and Language · Computer Science 2024-09-04 Chen Qian , Jie Zhang , Wei Yao , Dongrui Liu , Zhenfei Yin , Yu Qiao , Yong Liu , Jing Shao

Stable Diffusion revolutionised image creation from descriptive text. GPT-2, GPT-3(.5) and GPT-4 demonstrated astonishing performance across a variety of language tasks. ChatGPT introduced such language models to the general public. It is…

Machine Learning · Computer Science 2024-04-16 Ilia Shumailov , Zakhar Shumaylov , Yiren Zhao , Yarin Gal , Nicolas Papernot , Ross Anderson