English
Related papers

Related papers: IF-GUIDE: Influence Function-Guided Detoxification…

200 papers

Large language model (LLM) alignment is typically achieved through learning from human preference comparisons, making the quality of preference data critical to its success. Existing studies often pre-process raw training datasets to…

Machine Learning · Computer Science 2026-03-17 Zizhuo Zhang , Qizhou Wang , Shanshan Ye , Jianing Zhu , Jiangchao Yao , Bo Han , Masashi Sugiyama

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Computation and Language · Computer Science 2024-09-04 Bocheng Chen , Hanqing Guo , Guangjing Wang , Yuanda Wang , Qiben Yan

Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into…

Cryptography and Security · Computer Science 2023-10-31 Manli Shu , Jiongxiao Wang , Chen Zhu , Jonas Geiping , Chaowei Xiao , Tom Goldstein

Training data attribution (TDA) methods offer to trace a model's prediction on any given example back to specific influential training examples. Existing approaches do so by assigning a scalar influence score to each training example, under…

Machine Learning · Computer Science 2023-03-15 Kelvin Guu , Albert Webson , Ellie Pavlick , Lucas Dixon , Ian Tenney , Tolga Bolukbasi

While instruction-tuned language models have demonstrated impressive zero-shot generalization, these models often struggle to generate accurate responses when faced with instructions that fall outside their training set. This paper presents…

Computation and Language · Computer Science 2024-02-20 Taehyeon Kim , Joonkee Kim , Gihun Lee , Se-Young Yun

Instruction-following LLMs have recently allowed systems to discover hidden concepts from a collection of unstructured documents based on a natural language description of the purpose of the discovery (i.e., goal). Still, the quality of the…

Computation and Language · Computer Science 2025-04-29 Zhouhang Xie , Tushar Khot , Bhavana Dalvi Mishra , Harshit Surana , Julian McAuley , Peter Clark , Bodhisattwa Prasad Majumder

Recent studies show that instruction tuning (IT) and reinforcement learning from human feedback (RLHF) improve the abilities of large language models (LMs) dramatically. While these tuning methods can help align models with human objectives…

Artificial Intelligence · Computer Science 2024-04-02 Itay Itzhak , Gabriel Stanovsky , Nir Rosenfeld , Yonatan Belinkov

Large language models (LLMs) have demonstrated remarkable reasoning capabilities in math and coding, often bolstered by post-training on the chain-of-thoughts (CoTs) generated by stronger models. However, existing strategies for curating…

Machine Learning · Computer Science 2025-05-27 Siqi Kou , Qingyuan Tian , Hanwen Xu , Zihao Zeng , Zhijie Deng

We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. Given a training corpus and control criteria formulated as a sequence-level constraint on model outputs, our method fine-tunes the…

Computation and Language · Computer Science 2024-10-10 Tao Meng , Ninareh Mehrabi , Palash Goyal , Anil Ramakrishna , Aram Galstyan , Richard Zemel , Kai-Wei Chang , Rahul Gupta , Charith Peris

Recent breakthroughs in Large Language Models (LLMs) have revealed remarkable generative capabilities and emerging self-regulatory mechanisms, including self-correction and self-rewarding. However, current detoxification techniques rarely…

Computation and Language · Computer Science 2026-01-21 Kaituo Zhang , Zhimeng Jiang , Na Zou

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

We aim to construct a class of learning algorithms that are of practical value to applied researchers in fields such as biostatistics, epidemiology and econometrics, where the need to learn from incompletely observed information is…

Methodology · Statistics 2021-02-09 Alicia Curth , Ahmed M. Alaa , Mihaela van der Schaar

The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…

Cryptography and Security · Computer Science 2025-06-19 Wassim Bouaziz , Mathurin Videau , Nicolas Usunier , El-Mahdi El-Mhamdi

A critical step for reliable large language models (LLMs) use in healthcare is to attribute predictions to their training data, akin to a medical case study. This requires token-level precision: pinpointing not just which training examples…

Machine Learning · Computer Science 2026-05-14 Shixing Yu , Promit Ghosal , Kyra Gan

Influence functions estimate effect of individual data points on predictions of the model on test data and were adapted to deep learning in Koh and Liang [2017]. They have been used for detecting data poisoning, detecting helpful and…

Machine Learning · Computer Science 2022-10-04 Nikunj Saunshi , Arushi Gupta , Mark Braverman , Sanjeev Arora

Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data. To make the resulting model useful to users,…

Computation and Language · Computer Science 2026-01-30 Ajay Patel , Colin Raffel , Chris Callison-Burch

Quantifying the impact of training data points is crucial for understanding the outputs of machine learning models and for improving the transparency of the AI pipeline. The influence function is a principled and popular data attribution…

Machine Learning · Computer Science 2024-03-14 Yongchan Kwon , Eric Wu , Kevin Wu , James Zou

Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models (LLMs) due to their reduced computational and memory requirements. This paper investigates the effectiveness of these methods in…

Machine Learning · Computer Science 2024-05-30 Saswat Das , Marco Romanelli , Cuong Tran , Zarreen Reza , Bhavya Kailkhura , Ferdinando Fioretto

Good models require good training data. For overparameterized deep models, the causal relationship between training data and model predictions is increasingly opaque and poorly understood. Influence analysis partially demystifies training's…

Machine Learning · Computer Science 2024-04-02 Zayd Hammoudeh , Daniel Lowd

Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful. Nevertheless, some human instructions are often malicious or misleading and…

Computation and Language · Computer Science 2024-03-08 Rui Wang , Hongru Wang , Fei Mi , Yi Chen , Boyang Xue , Kam-Fai Wong , Ruifeng Xu