English
Related papers

Related papers: Reckoning with the Disagreement Problem: Explanati…

200 papers

Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous human preferences. In practice, systematic annotator and user-group disagreement makes mean-reward…

Machine Learning · Computer Science 2026-05-19 Mingxi Zou , Jiaxiang Chen , Junfan Li , Langzhang Liang , Qifan Wang , Xu Yinghui , Zenglin Xu

Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal preference data. When human annotators provide graded preferences…

Machine Learning · Computer Science 2026-03-04 Amirhossein Afsharrad , Ruida Zhou , Luca Viano , Sanjay Lall , Mohammad Ghavamzadeh

As machine learning models are increasingly deployed in high-stakes domains such as legal and financial decision-making, there has been growing interest in post-hoc methods for generating counterfactual explanations. Such explanations…

Machine Learning · Computer Science 2022-03-22 Alexis Ross , Himabindu Lakkaraju , Osbert Bastani

As performance gains through scaling data and/or model size experience diminishing returns, it is becoming increasingly popular to turn to ensembling, where the predictions of multiple models are combined to improve accuracy. In this paper,…

Machine Learning · Statistics 2024-11-04 Hyunsuk Kim , Liam Hodgkinson , Ryan Theisen , Michael W. Mahoney

Safe deployment of AI models requires proactive detection of failures to prevent costly errors. To this end, we study the important problem of detecting failures in deep regression models. Existing approaches rely on epistemic uncertainty…

Machine Learning · Computer Science 2024-06-04 Jayaraman J. Thiagarajan , Vivek Narayanaswamy , Puja Trivedi , Rushil Anirudh

Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to…

Information Retrieval · Computer Science 2018-12-04 Wenting Xiong , Iftitahu Ni'mah , Juan M. G. Huesca , Werner van Ipenburg , Jan Veldsink , Mykola Pechenizkiy

Historical interactions are the default choice for recommender model training, which typically exhibit high sparsity, i.e., most user-item pairs are unobserved missing data. A standard choice is treating the missing data as negative…

Information Retrieval · Computer Science 2023-07-31 Chenxu Wang , Fuli Feng , Yang Zhang , Qifan Wang , Xunhan Hu , Xiangnan He

Speech emotion recognition (SER) has gained significant attention due to its several application fields, such as mental health, education, and human-computer interaction. However, the accuracy of SER systems is hindered by high-dimensional…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-07 Alaa Nfissi , Wassim Bouachir , Nizar Bouguila , Brian Mishara

Instruction-following is a fundamental capability of language models, requiring the model to recognize even the most subtle requirements in the instructions and accurately reflect them in its output. Such an ability is well-suited for and…

Computation and Language · Computer Science 2025-03-18 Jiale Cheng , Xiao Liu , Cunxiang Wang , Xiaotao Gu , Yida Lu , Dan Zhang , Yuxiao Dong , Jie Tang , Hongning Wang , Minlie Huang

Disagreement-based approaches generate multiple classifiers and exploit the disagreement among them with unlabeled data to improve learning performance. Co-training is a representative paradigm of them, which trains two classifiers…

Machine Learning · Computer Science 2017-08-16 Wei Wang , Zhi-Hua Zhou

Embedding paralinguistic properties is a challenging task as there are only a few hours of training data available for domains such as emotional speech. One solution to this problem is to pretrain a general self-supervised speech…

Computation and Language · Computer Science 2022-11-04 Florian Lux , Ching-Yi Chen , Ngoc Thang Vu

How do neural language models keep track of number agreement between subject and verb? We show that `diagnostic classifiers', trained to predict number from the internal states of a language model, provide a detailed understanding of how,…

Computation and Language · Computer Science 2021-11-19 Mario Giulianelli , Jacqueline Harding , Florian Mohnert , Dieuwke Hupkes , Willem Zuidema

Post-hoc explainability methods aim to clarify predictions of black-box machine learning models. However, it is still largely unclear how well users comprehend the provided explanations and whether these increase the users ability to…

Machine Learning · Computer Science 2023-09-22 Anahid Jalali , Bernhard Haslhofer , Simone Kriglstein , Andreas Rauber

Deep Neural Networks are often brittle on image classification tasks and known to misclassify inputs. While these misclassifications may be inevitable, all failure modes cannot be considered equal. Certain misclassifications (eg.…

Machine Learning · Computer Science 2021-11-03 Alberto Olmo , Sailik Sengupta , Subbarao Kambhampati

AI explainability improves the transparency of models, making them more trustworthy. Such goals are motivated by the emergence of deep learning models, which are obscure by nature; even in the domain of images, where deep learning has…

Machine Learning · Computer Science 2022-03-01 Anna Arias-Duart , Ferran Parés , Dario Garcia-Gasulla , Victor Gimenez-Abalos

In multi-turn dialogues, large language models (LLM) face a critical challenge of ensuring coherence while adapting to user-specific information. This study introduces the persona knowledge gap, the discrepancy between a model's internal…

Computation and Language · Computer Science 2025-03-18 Sarvesh Baskar , Tanmay Tulsidas Verelakar , Srinivasan Parthasarathy , Manas Gaur

Model calibration aims to align confidence with prediction correctness. The Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Yuchi Liu , Lei Wang , Yuli Zou , James Zou , Liang Zheng

We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that humans have the ability to make quick, intuitive decisions as…

Machine Learning · Computer Science 2025-03-05 Johannes Schneider , Michalis Vlachos

Connectionist Temporal Classification (CTC) is a widely used criterion for training supervised sequence-to-sequence (seq2seq) models. It enables learning the relations between input and output sequences, termed alignments, by marginalizing…

Computation and Language · Computer Science 2024-03-08 Eliya Segev , Maya Alroy , Ronen Katsir , Noam Wies , Ayana Shenhav , Yael Ben-Oren , David Zar , Oren Tadmor , Jacob Bitterman , Amnon Shashua , Tal Rosenwein

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