English
Related papers

Related papers: Exploitation Without Deception: Dark Triad Feature…

200 papers

Existing works are dedicated to untangling atomized numerical components (features) from the hidden states of Large Language Models (LLMs). However, they typically rely on autoencoders constrained by some training-time regularization on…

Machine Learning · Computer Science 2026-02-13 Hakaze Cho , Haolin Yang , Yanshu Li , Brian M. Kurkoski , Naoya Inoue

Large language models (LLMs) often exhibit sycophantic behaviors -- such as excessive agreement with or flattery of the user -- but it is unclear whether these behaviors arise from a single mechanism or multiple distinct processes. We…

Computation and Language · Computer Science 2026-03-24 Daniel Vennemeyer , Phan Anh Duong , Tiffany Zhan , Tianyu Jiang

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a…

Machine Learning · Computer Science 2025-09-24 Dong Shu , Xuansheng Wu , Haiyan Zhao , Daking Rai , Ziyu Yao , Ninghao Liu , Mengnan Du

Large Language Models (LLMs) are powerful and widely adopted, but their practical impact is limited by the well-known hallucination phenomenon. While recent hallucination detection methods have made notable progress, we find most of them…

Computation and Language · Computer Science 2026-04-21 Boshui Chen , Zhaoxin Fan , Ke Wang , Zhiying Leng , Faguo Wu , Hongwei Zheng , Yifan Sun , Wenjun Wu

Recently, pre-trained language models mostly follow the pre-train-then-fine-tuning paradigm and have achieved great performance on various downstream tasks. However, since the pre-training stage is typically task-agnostic and the…

Computation and Language · Computer Science 2020-10-08 Yuxian Gu , Zhengyan Zhang , Xiaozhi Wang , Zhiyuan Liu , Maosong Sun

As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important to ensure that they are unbiased. In this paper, we argue that the predominant approach of simply…

Computers and Society · Computer Science 2026-01-13 Addison J. Wu , Ryan Liu , Xuechunzi Bai , Thomas L. Griffiths

Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques that mitigate such biases. In this work, we perform an…

Computation and Language · Computer Science 2022-04-05 Nicholas Meade , Elinor Poole-Dayan , Siva Reddy

Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompting and activation steering expose *different*, architecture-dependent vulnerability…

Artificial Intelligence · Computer Science 2026-04-15 Wenkai Li , Fan Yang , Shaunak A. Mehta , Koichi Onoue

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making contexts. While prior work has shown that LLMs exhibit cognitive biases behaviorally, whether these biases correspond to identifiable internal…

Artificial Intelligence · Computer Science 2026-04-03 Fan Huang , Songheng Zhang , Haewoon Kwak , Jisun An

Sensitive attributes are legally protected characteristics that should not be used to discriminate. Careful steps have been taken to minimize the risk of human bias regarding these fields, such as race and age. Large language models (LLMs)…

Computers and Society · Computer Science 2026-04-14 Anay Agarwalla , Simeon Sayer

We propose affine concept editing (ACE) as an approach for steering language models' behavior by intervening directly in activations. We begin with an affine decomposition of model activation vectors and show that prior methods for steering…

Machine Learning · Computer Science 2025-01-29 Thomas Marshall , Adam Scherlis , Nora Belrose

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior.…

Machine Learning · Computer Science 2026-02-06 Xu Wang , Bingqing Jiang , Yu Wan , Baosong Yang , Lingpeng Kong , Difan Zou

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Machine Learning · Computer Science 2023-10-05 Hoagy Cunningham , Aidan Ewart , Logan Riggs , Robert Huben , Lee Sharkey

We investigate empathy-in-action -- the willingness to sacrifice task efficiency to address human needs -- as a linear direction in LLM activation space. Using contrastive prompts grounded in the Empathy-in-Action (EIA) benchmark, we test…

Computation and Language · Computer Science 2025-11-24 Juan P. Cadile

Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to…

Computer Vision and Pattern Recognition · Computer Science 2019-12-30 Anupriya Gogna , Angshul Majumdar

Large language models (LLMs) have shown remarkable success in recent years, enabling a wide range of applications, including intelligent assistants that support users' daily life and work. A critical factor in building such assistants is…

Computation and Language · Computer Science 2025-10-28 Xiaoyan Zhao , Ming Yan , Yilun Qiu , Haoting Ni , Yang Zhang , Fuli Feng , Hong Cheng , Tat-Seng Chua

Although sparse autoencoders (SAEs) are crucial for identifying interpretable features in neural networks, it is still challenging to distinguish between real computational patterns and erroneous correlations. We introduce Model-X knockoffs…

Machine Learning · Computer Science 2025-11-18 Tsogt-Ochir Enkhbayar

Sparse Autoencoders (SAEs) have emerged as a predominant tool in mechanistic interpretability, aiming to identify interpretable monosemantic features. However, how does sparse encoding organize the representations of activation vector from…

Machine Learning · Computer Science 2025-05-29 Wenjie Sun , Bingzhe Wu , Zhile Yang , Chengke Wu

Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single…

Machine Learning · Computer Science 2026-04-07 Matthew Levinson

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…

Machine Learning · Computer Science 2025-07-30 Viktoria Schuster
‹ Prev 1 8 9 10 Next ›