English
Related papers

Related papers: Non-linear Interventions on Large Language Models

200 papers

Large Language Models (LLMs) may portray discrimination towards certain individuals, especially those characterized by multiple attributes (aka intersectional bias). Discovering intersectional bias in LLMs is challenging, as it involves…

Computation and Language · Computer Science 2025-03-18 Badr Souani , Ezekiel Soremekun , Mike Papadakis , Setsuko Yokoyama , Sudipta Chattopadhyay , Yves Le Traon

There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…

Computation and Language · Computer Science 2021-12-14 Nicola De Cao , Leon Schmid , Dieuwke Hupkes , Ivan Titov

Large language models (LLMs) have demonstrated emergent abilities across diverse tasks, raising the question of whether they acquire internal world models. In this work, we investigate whether LLMs implicitly encode linear spatial world…

Artificial Intelligence · Computer Science 2025-06-04 Matthieu Tehenan , Christian Bolivar Moya , Tenghai Long , Guang Lin

There is a large ongoing scientific effort in mechanistic interpretability to map embeddings and internal representations of AI systems into human-understandable concepts. A key element of this effort is the linear representation…

Machine Learning · Computer Science 2025-05-27 Alexander Modell , Patrick Rubin-Delanchy , Nick Whiteley

This paper explores the critical but often overlooked role of non-verbal cues, including co-speech gestures and facial expressions, in human communication and their implications for Natural Language Processing (NLP). We argue that…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-14 Amit Moryossef

Causal representation learning (CRL) offers the promise of uncovering the underlying causal model by which observed data was generated, but the practical applicability of existing methods remains limited by the strong assumptions required…

Machine Learning · Computer Science 2026-01-30 Yuhang Liu , Zhen Zhang , Dong Gong , Erdun Gao , Biwei Huang , Mingming Gong , Anton van den Hengel , Kun Zhang , Javen Qinfeng Shi

Regression models are used in a wide range of applications providing a powerful scientific tool for researchers from different fields. Linear, or simple parametric, models are often not sufficient to describe complex relationships between…

Machine Learning · Statistics 2021-11-24 Aliaksandr Hubin , Geir Storvik , Florian Frommlet

Unsupervised mixture learning (UML) aims at identifying linearly or nonlinearly mixed latent components in a blind manner. UML is known to be challenging: Even learning linear mixtures requires highly nontrivial analytical tools, e.g.,…

Machine Learning · Computer Science 2022-10-17 Qi Lyu , Xiao Fu

Graph representation learning methods are highly effective in handling complex non-Euclidean data by capturing intricate relationships and features within graph structures. However, traditional methods face challenges when dealing with…

Machine Learning · Computer Science 2025-02-25 Hang Gao , Chenhao Zhang , Fengge Wu , Junsuo Zhao , Changwen Zheng , Huaping Liu

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Computation and Language · Computer Science 2025-02-27 Sumanta Bhattacharyya , Pedram Rooshenas

Steering methods influence Large Language Model behavior by identifying semantic directions in hidden representations, but are typically realized through inference-time activation interventions that apply a fixed, global modification to the…

Computation and Language · Computer Science 2026-03-04 Chung-En Sun , Ge Yan , Zimo Wang , Tsui-Wei Weng

Large Language Models (LLMs) have demonstrated remarkable generalization capabilities across tasks and languages, revolutionizing natural language processing. This paper investigates the naturally emerging representation alignment in LLMs,…

Model-agnostic tools for interpreting machine-learning models struggle to summarize the joint effects of strongly dependent features in high-dimensional feature spaces, which play an important role in pattern recognition, for example in…

Machine Learning · Computer Science 2023-06-01 Alexander Brenning

Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and…

Artificial Intelligence · Computer Science 2025-11-11 Hirohane Takagi , Gouki Minegishi , Shota Kizawa , Issey Sukeda , Hitomi Yanaka

In-context learning (ICL) is an important paradigm for adapting large language models (LLMs) to new tasks, but the generalization behavior of ICL remains poorly understood. We investigate the inductive biases of ICL from the perspective of…

Computation and Language · Computer Science 2023-05-23 Chenglei Si , Dan Friedman , Nitish Joshi , Shi Feng , Danqi Chen , He He

Large Language models (LLMs), such as ChatGPT, have gained popularity in recent years with the advancement of Natural Language Processing (NLP), with use cases spanning many disciplines and daily lives as well. LLMs inherit explicit and…

Computation and Language · Computer Science 2025-12-01 Fatima Kazi

Large Language Models (LLMs) have been shown to exhibit various biases and stereotypes in their generated content. While extensive research has investigated biases in LLMs, prior work has predominantly focused on explicit bias, with minimal…

Computation and Language · Computer Science 2025-06-04 Yachao Zhao , Bo Wang , Yan Wang , Dongming Zhao , Ruifang He , Yuexian Hou

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore…

Machine Learning · Computer Science 2024-03-19 Hao Sun

Negation has been shown to be a major bottleneck for masked language models, such as BERT. However, whether this finding still holds for larger-sized auto-regressive language models (``LLMs'') has not been studied comprehensively. With the…

Computation and Language · Computer Science 2023-06-16 Thinh Hung Truong , Timothy Baldwin , Karin Verspoor , Trevor Cohn

Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…

Information Retrieval · Computer Science 2025-01-22 Chao Zhang , Haoxin Zhang , Shiwei Wu , Di Wu , Tong Xu , Xiangyu Zhao , Yan Gao , Yao Hu , Enhong Chen