English
Related papers

Related papers: SEAT: Sparse Entity-Aware Tuning for Knowledge Ada…

200 papers

Sparse autoencoders (SAEs) have received considerable recent attention as tools for mechanistic interpretability, showing success at extracting interpretable features even from very large LLMs. However, this research has been largely…

Machine Learning · Computer Science 2025-05-20 Jeremy Budd , Javier Ideami , Benjamin Macdowall Rynne , Keith Duggar , Randall Balestriero

How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning models trained via a novel and efficient sparse autoencoder…

Computation and Language · Computer Science 2025-06-17 Shangshang Wang , Julian Asilis , Ömer Faruk Akgül , Enes Burak Bilgin , Ollie Liu , Deqing Fu , Willie Neiswanger

Large language models (LLMs) risk retaining sensitive, copyrighted, or harmful information from their training data. Entity-level unlearning addresses this issue by removing all knowledge of a specific entity while preserving the model's…

Computation and Language · Computer Science 2026-01-15 Xiaoqi Han , Víctor Gutiérrez-Basulto , Ru Li , Xiaoli Li , Jiye Liang , Jeff Z. Pan

While the self-attention mechanism has been widely used in a wide variety of tasks, it has the unfortunate property of a quadratic cost with respect to the input length, which makes it difficult to deal with long inputs. In this paper, we…

Computation and Language · Computer Science 2020-09-30 Xiaoya Li , Yuxian Meng , Mingxin Zhou , Qinghong Han , Fei Wu , Jiwei Li

Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…

Information Retrieval · Computer Science 2025-02-25 Hao Kang , Tevin Wang , Chenyan Xiong

Several works have proven that finetuning is an applicable approach for debiasing contextualized word embeddings. Similarly, discrete prompts with semantic meanings have shown to be effective in debiasing tasks. With unfixed mathematical…

Computation and Language · Computer Science 2025-05-27 Ke Yang , Charles Yu , Yi Fung , Manling Li , Heng Ji

Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss between the original model logits and the reconstructed model logits when replacing model…

Machine Learning · Computer Science 2025-04-01 Adam Karvonen

Large Language Models often generate unfaithful responses in knowledge intensive tasks due to knowledge conflict,that is,a preference for relying on internal parametric knowledge rather than the provided context.To address this issue,we…

Computation and Language · Computer Science 2025-09-15 Shengqiang Fu

The Efficient Adaptive Transformer (EAT) framework unifies three adaptive efficiency techniques - progressive token pruning, sparse attention, and dynamic early exiting - into a single, reproducible architecture for input-adaptive…

Computation and Language · Computer Science 2025-10-16 Jan Miller

Speech emotion recognition (SER) plays a critical role in building emotion-aware speech systems, but its performance degrades significantly under noisy conditions. Although speech enhancement (SE) can improve robustness, it often introduces…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-29 Jing-Tong Tzeng , Carlos Busso , Chi-Chun Lee

Symmetry, a fundamental concept to understand our environment, often oversimplifies reality from a mathematical perspective. Humans are a prime example, deviating from perfect symmetry in terms of appearance and cognitive biases (e.g.…

Machine Learning · Computer Science 2025-02-11 Miguel Abreu , Luis Paulo Reis , Nuno Lau

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as…

Machine Learning · Computer Science 2026-03-04 Xuan Yang , Jiayu Liu , Yuhang Lai , Hao Xu , Zhenya Huang , Ning Miao

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

Machine Learning · Computer Science 2026-03-03 Shruti Joshi , Andrea Dittadi , Sébastien Lachapelle , Dhanya Sridhar

Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…

Machine Learning · Computer Science 2026-02-10 Zahra Rahimi Afzal , Tara Esmaeilbeig , Mojtaba Soltanalian , Mesrob I. Ohannessian

Semi-supervised learning is attracting blooming attention, due to its success in combining unlabeled data. To mitigate potentially incorrect pseudo labels, recent frameworks mostly set a fixed confidence threshold to discard uncertain…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Lihe Yang , Zhen Zhao , Lei Qi , Yu Qiao , Yinghuan Shi , Hengshuang Zhao

Sparse autoencoders (SAEs) have emerged as powerful techniques for interpretability of large language models (LLMs), aiming to decompose hidden states into meaningful semantic features. While several SAE variants have been proposed, there…

Machine Learning · Computer Science 2025-10-03 Xudong Zhu , Mohammad Mahdi Khalili , Zhihui Zhu

Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses. Understanding their internal states is crucial for understanding their successes, diagnosing their failures,…

Computation and Language · Computer Science 2025-02-24 Xuansheng Wu , Jiayi Yuan , Wenlin Yao , Xiaoming Zhai , Ninghao Liu

Mitigating hallucinations in Large Language Models (LLMs) is critical for their reliable deployment. Existing methods typically fine-tune LLMs to abstain from answering questions beyond their knowledge scope. However, these methods often…

Computation and Language · Computer Science 2025-10-29 Hao An , Yang Xu

Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine…

Computation and Language · Computer Science 2024-10-16 YuXuan Wu , Bonaventure F. P. Dossou , Dianbo Liu

In recent years, continual learning with pre-training (CLPT) has received widespread interest, instead of its traditional focus of training from scratch. The use of strong pre-trained models (PTMs) can greatly facilitate knowledge transfer…

Computer Vision and Pattern Recognition · Computer Science 2024-08-16 Gengwei Zhang , Liyuan Wang , Guoliang Kang , Ling Chen , Yunchao Wei