English
Related papers

Related papers: Subliminal Signals in Preference Labels

200 papers

Classification is an essential and fundamental task in machine learning, playing a cardinal role in the field of natural language processing (NLP) and computer vision (CV). In a supervised learning setting, labels are always needed for the…

Computation and Language · Computer Science 2021-02-04 Irene Li

The "LLM-as-a-Judge" paradigm, using Large Language Models (LLMs) as automated evaluators, is pivotal to LLM development, offering scalable feedback for complex tasks. However, the reliability of these judges is compromised by various…

Computation and Language · Computer Science 2026-05-22 Qingquan Li , Shaoyu Dou , Kailai Shao , Chao Chen , Haixiang Hu

To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Yun-Chun Chen , Chao-Te Chou , Yu-Chiang Frank Wang

Discrimination can occur when the underlying unbiased labels are overwritten by an agent with potential bias, resulting in biased datasets that unfairly harm specific groups and cause classifiers to inherit these biases. In this paper, we…

Machine Learning · Computer Science 2023-12-27 Yixuan Zhang , Boyu Li , Zenan Ling , Feng Zhou

The field of preference optimization has made outstanding contributions to the alignment of language models with human preferences. Despite these advancements, recent methods still rely heavily on substantial paired (labeled) feedback data,…

Machine Learning · Computer Science 2026-02-20 Seonggyun Lee , Sungjun Lim , Seojin Park , Soeun Cheon , Kyungwoo Song

We consider the task of training classifiers without labels. We propose a weakly supervised method---adversarial label learning---that trains classifiers to perform well against an adversary that chooses labels for training data. The weak…

Machine Learning · Computer Science 2019-01-31 Chidubem Arachie , Bert Huang

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

Semi-supervised algorithms aim to learn prediction functions from a small set of labeled observations and a large set of unlabeled observations. Because this framework is relevant in many applications, they have received a lot of interest…

Machine Learning · Computer Science 2025-02-17 Massih-Reza Amini , Vasilii Feofanov , Loic Pauletto , Lies Hadjadj , Emilie Devijver , Yury Maximov

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to…

Computer Vision and Pattern Recognition · Computer Science 2020-11-18 Longhui Wei , Lingxi Xie , Jianzhong He , Jianlong Chang , Xiaopeng Zhang , Wengang Zhou , Houqiang Li , Qi Tian

Self-preference is a fundamental feature of biological organisms. Since large language models (LLMs) lack sentience, they might be expected to avoid such distortions. Yet, across 72 experiments and ~41,000 queries, we discovered massive…

Artificial Intelligence · Computer Science 2026-05-20 Steven A. Lehr , Mary Cipperman , Mahzarin R. Banaji

Preference-driven behavior in LLMs may be a necessary precondition for AI misalignment such as sandbagging: models cannot strategically pursue misaligned goals unless their behavior is influenced by their preferences. Yet prior work has…

Artificial Intelligence · Computer Science 2026-02-24 Katarina Slama , Alexandra Souly , Dishank Bansal , Henry Davidson , Christopher Summerfield , Lennart Luettgau

Large Language Models (LLMs) are increasingly used in tasks such as psychological text analysis and decision-making in automated workflows. However, their reliability remains a concern due to potential biases inherited from their training…

Computation and Language · Computer Science 2025-04-29 Yi-Long Lu , Chunhui Zhang , Wei Wang

Neural networks are powered by an implicit bias: a tendency of gradient descent to fit training data in a way that generalizes to unseen data. A recent class of neural network models gaining increasing popularity is structured state space…

Machine Learning · Computer Science 2025-12-16 Yonatan Slutzky , Yotam Alexander , Noam Razin , Nadav Cohen

In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on a set of unlabeled data. The aim is to build useful representations that can be used in downstream tasks, without costly…

Machine Learning · Computer Science 2020-11-11 Massimiliano Patacchiola , Amos Storkey

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

Although value-aligned language models (LMs) appear unbiased in explicit bias evaluations, they often exhibit stereotypes in implicit word association tasks, raising concerns about their fair usage. We investigate the mechanisms behind this…

Computation and Language · Computer Science 2025-06-10 Lihao Sun , Chengzhi Mao , Valentin Hofmann , Xuechunzi Bai

LLMs are increasingly used to make or support high-stakes decisions under uncertainty, where alignment depends not only on factual accuracy but on how models weigh tradeoffs between different outcomes. We present an empirical pipeline for…

Machine Learning · Computer Science 2026-05-12 Khurram Yamin , Jingjing Tang , Eric Horvitz , Bryan Wilder

Common machine learning settings range from supervised tasks, where accurately labeled data is accessible, through semi-supervised and weakly-supervised tasks, where target labels are scant or noisy, to unsupervised tasks where labels are…

Machine Learning · Computer Science 2025-04-22 Yogev Kriger , Shai Fine

Semi-supervised learning by self-training heavily relies on pseudo-label selection (PLS). The selection often depends on the initial model fit on labeled data. Early overfitting might thus be propagated to the final model by selecting…

Machine Learning · Statistics 2023-06-27 Julian Rodemann , Jann Goschenhofer , Emilio Dorigatti , Thomas Nagler , Thomas Augustin

Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches…

Machine Learning · Computer Science 2024-10-14 Wei Wang , Takashi Ishida , Yu-Jie Zhang , Gang Niu , Masashi Sugiyama