English
Related papers

Related papers: Resa: Transparent Reasoning Models via SAEs

200 papers

Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network's internal activations. However, SAEs are traditionally trained considering…

Machine Learning · Computer Science 2025-04-02 Jeffrey Olmo , Jared Wilson , Max Forsey , Bryce Hepner , Thomas Vin Howe , David Wingate

Sparse autoencoders (SAEs) are a core interpretability tool for large language models, and progress on SAE architectures depends on benchmarks that reliably distinguish better SAEs from worse ones. We audit the SAE quality metrics in…

Machine Learning · Computer Science 2026-05-19 David Chanin

As humans, we are natural any-horizon reasoners, i.e., we can decide whether to iteratively skim long videos or watch short ones in full when necessary for a given task. With this in mind, one would expect video reasoning models to reason…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Jitesh Jain , Jialuo Li , Zixian Ma , Jieyu Zhang , Chris Dongjoo Kim , Sangho Lee , Rohun Tripathi , Tanmay Gupta , Christopher Clark , Humphrey Shi

Sparse autoencoders (SAEs) are commonly used to interpret the internal activations of large language models (LLMs) by mapping them to human-interpretable concept representations. While existing evaluations of SAEs focus on metrics such as…

Machine Learning · Computer Science 2026-01-26 Aaron J. Li , Suraj Srinivas , Usha Bhalla , Himabindu Lakkaraju

Adapting LLMs with new knowledge is increasingly important, but standard fine-tuning often erodes aligned epistemic abstention: the ability to acknowledge when the model does not know. This failure mode is especially concerning in…

Artificial Intelligence · Computer Science 2026-04-22 William F. Shen , Xinchi Qiu , Nicola Cancedda , Nicholas D. Lane

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

Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured…

Computation and Language · Computer Science 2024-09-30 Guoxin Chen , Kexin Tang , Chao Yang , Fuying Ye , Yu Qiao , Yiming Qian

Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant challenge. We introduce a suite of 256 SAEs, trained on each…

Model training requires significantly more memory, compared with inference. Parameter efficient fine-tuning (PEFT) methods provide a means of adapting large models to downstream tasks using less memory. However, existing methods such as…

Machine Learning · Computer Science 2024-07-11 Marawan Gamal Abdel Hameed , Aristides Milios , Siva Reddy , Guillaume Rabusseau

What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the…

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

Machine Learning · Computer Science 2025-10-10 Yifei Yao , Mengnan Du

Sparse Autoencoders (SAEs) have emerged as a promising tool for interpreting neural networks by decomposing their activations into sparse sets of human-interpretable features. Recent work has introduced multiple SAE variants and…

Machine Learning · Computer Science 2026-02-17 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Rogov , Ivan Oseledets , Elena Tutubalina

Multi-trait automated essay scoring (AES) systems provide a fine-grained evaluation of an essay's diverse aspects. While they excel in scoring, prior systems fail to explain why specific trait scores are assigned. This lack of transparency…

Computation and Language · Computer Science 2025-03-03 Heejin Do , Sangwon Ryu , Gary Geunbae Lee

Text-prompted image segmentation enables fine-grained visual understanding and is critical for applications such as human-computer interaction and robotics. However, existing supervised fine-tuning methods typically ignore explicit…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Lianghui Zhu , Bin Ouyang , Yuxuan Zhang , Tianheng Cheng , Rui Hu , Haocheng Shen , Longjin Ran , Xiaoxin Chen , Li Yu , Wenyu Liu , Xinggang Wang

Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

Machine Learning · Computer Science 2025-02-13 Gonçalo Paulo , Stepan Shabalin , Nora Belrose

Large Language Models have achieved remarkable success across various natural language processing tasks, yet their high computational cost during inference remains a major bottleneck. This paper introduces Sparse Expert Activation Pruning…

Computation and Language · Computer Science 2025-03-11 Xun Liang , Hanyu Wang , Huayi Lai , Simin Niu , Shichao Song , Jiawei Yang , Jihao Zhao , Feiyu Xiong , Bo Tang , Zhiyu Li

While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems…

Computation and Language · Computer Science 2025-05-28 Yang He , Xiao Ding , Bibo Cai , Yufei Zhang , Kai Xiong , Zhouhao Sun , Bing Qin , Ting Liu

Incorporating explicit reasoning rules within the latent space of language models (LMs) offers a promising pathway to enhance generalisation, interpretability, and controllability. While current Transformer-based language models have shown…

Computation and Language · Computer Science 2025-10-13 Yingji Zhang , Marco Valentino , Danilo S. Carvalho , André Freitas

While Small Language Models (SLMs) have demonstrated promising performance on an increasingly wide array of commonsense reasoning benchmarks, current evaluation practices rely almost exclusively on the accuracy of their final answers,…

Computation and Language · Computer Science 2026-04-21 Francesco Maria Molfese , Luca Moroni , Ciro Porcaro , Simone Conia , Roberto Navigli

The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their substantial demands on memory, processing power, and energy…

Machine Learning · Computer Science 2024-07-02 Enshu Liu , Junyi Zhu , Zinan Lin , Xuefei Ning , Matthew B. Blaschko , Shengen Yan , Guohao Dai , Huazhong Yang , Yu Wang