English
Related papers

Related papers: Revisiting LRP: Positional Attribution as the Miss…

200 papers

Reinforcement learning (RL) often encounters delayed and sparse feedback in real-world applications, even with only episodic rewards. Previous approaches have made some progress in reward redistribution for credit assignment but still face…

Machine Learning · Computer Science 2025-01-10 Yun Qu , Yuhang Jiang , Boyuan Wang , Yixiu Mao , Cheems Wang , Chang Liu , Xiangyang Ji

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Xuanchang Zhang , Yifan Hao , Zhou Yu , Ziji Zhang , Abhinav Gullapalli , Hao Chen , Jing Huang , Tong Zhang

The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward…

Machine Learning · Computer Science 2021-12-22 Tom Bewley , Freddy Lecue

A promising approach to preserving model performance in linearized transformers is to employ position-based re-weighting functions. However, state-of-the-art re-weighting functions rely heavily on target sequence lengths, making it…

Computation and Language · Computer Science 2024-05-24 Victor Agostinelli , Sanghyun Hong , Lizhong Chen

A key goal of current mechanistic interpretability research in NLP is to find linear features (also called "feature vectors") for transformers: directions in activation space corresponding to concepts that are used by a given model in its…

Machine Learning · Computer Science 2024-06-05 Jacob Dunefsky , Arman Cohan

Interpretability is often pointed out as a key requirement for trustworthy machine learning. However, learning and releasing models that are inherently interpretable leaks information regarding the underlying training data. As such…

Artificial Intelligence · Computer Science 2024-04-04 Julien Ferry , Ulrich Aïvodji , Sébastien Gambs , Marie-José Huguet , Mohamed Siala

The widespread adoption of large language models (LLMs) across industries has increased the demand for high-quality and customizable outputs. However, traditional alignment methods often require retraining large pretrained models, making it…

Computation and Language · Computer Science 2025-12-16 Yi Liu , Dianqing Liu , Mingye Zhu , Junbo Guo , Yongdong Zhang , Zhendong Mao

Recent advances highlight Reinforcement Learning with Verifiable Rewards (RLVR) as a promising method for enhancing LLMs' capabilities. However, it remains unclear whether the current practice of RLVR truly expands a model's reasoning…

Machine Learning · Computer Science 2026-02-05 Fang Wu , Weihao Xuan , Ximing Lu , Mingjie Liu , Yi Dong , Zaid Harchaoui , Yejin Choi

Transformers achieve remarkable performance in various domains, including NLP, CV, audio processing, and graph analysis. However, they do not scale well on long sequence tasks due to their quadratic complexity w.r.t. the inputs length.…

Machine Learning · Computer Science 2022-02-24 Maksim Zubkov , Daniil Gavrilov

The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use of neural networks. While various approaches aiming towards…

Machine Learning · Statistics 2019-05-15 Raphael Suter , Đorđe Miladinović , Bernhard Schölkopf , Stefan Bauer

Decomposing a deep neural network's learned representations into interpretable features could greatly enhance its safety and reliability. To better understand features, we adopt a geometric perspective, viewing them as a learned coordinate…

Machine Learning · Computer Science 2025-04-30 Aryeh Brill

Machine comprehension plays an essential role in NLP and has been widely explored with dataset like MCTest. However, this dataset is too simple and too small for learning true reasoning abilities. \cite{hermann2015teaching} therefore…

Computation and Language · Computer Science 2016-05-16 Tian Tian , Yuezhang Li

Multi-layer perceptrons (MLP) have proven to be effective scene encoders when combined with higher-dimensional projections of the input, commonly referred to as \textit{positional encoding}. However, scenes with a wide frequency spectrum…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Zoe Landgraf , Alexander Sorkine Hornung , Ricardo Silveira Cabral

Transformer architectures rely on explicit position encodings in order to preserve a notion of word order. In this paper, we argue that existing work does not fully utilize position information. For example, the initial proposal of a…

Computation and Language · Computer Science 2020-09-30 Zhiheng Huang , Davis Liang , Peng Xu , Bing Xiang

Transfer learning is focused on the reuse of supervised learning models in a new context. Prominent applications can be found in robotics, image processing or web mining. In these fields, the learning scenarios are naturally changing but…

Machine Learning · Computer Science 2020-07-15 Christoph Raab , Frank-Michael Schleif

The lack of transparency of neural networks stays a major break for their use. The Layerwise Relevance Propagation technique builds heat-maps representing the relevance of each input in the model s decision. The relevance spreads backward…

Machine Learning · Computer Science 2020-02-26 Mathilde Guillemot , Catherine Heusele , Rodolphe Korichi , Sylvianne Schnebert , Liming Chen

Position information is essential for language modeling. In softmax transformers, Rotary Position Embeddings (\textit{RoPE}) encode positions through \textit{fixed-angle} rotations, while in linear transformers, order is handled via…

Computation and Language · Computer Science 2026-04-27 Sajad Movahedi , Timur Carstensen , Arshia Afzal , Frank Hutter , Antonio Orvieto , Volkan Cevher

Deep neural networks are widely used in practical applications of AI, however, their inner structure and complexity made them generally not easily interpretable. Model transparency and interpretability are key requirements for multiple…

Machine Learning · Computer Science 2026-01-13 Luca Bergamin , Roberto Confalonieri , Fabio Aiolli

Model agnostic feature attribution algorithms (such as SHAP and LIME) are ubiquitous techniques for explaining the decisions of complex classification models, such as deep neural networks. However, since complex classification models…

Machine Learning · Computer Science 2022-11-29 Ron Bitton , Alon Malach , Amiel Meiseles , Satoru Momiyama , Toshinori Araki , Jun Furukawa , Yuval Elovici , Asaf Shabtai

Local explanations of learning-to-rank (LTR) models are thought to extract the most important features that contribute to the ranking predicted by the LTR model for a single data point. Evaluating the accuracy of such explanations is…

Machine Learning · Statistics 2022-03-17 Amir Hossein Akhavan Rahnama , Judith Butepage