Related papers: GPT and Prejudice: A Sparse Approach to Understand…

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most…

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in…

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable…

This paper investigates gender bias in Large Language Model (LLM)-generated teacher evaluations in higher education setting, focusing on evaluations produced by GPT-4 across six academic subjects. By applying a comprehensive analytical…

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…

Understanding whether large language models (LLMs) capture structured meaning requires examining how they represent concept relationships. In this work, we study three models of increasing scale: Pythia-70M, GPT-2, and Llama 3.1 8B,…

Large language models (LLMs) are becoming pervasive in everyday life, yet their propensity to reproduce biases inherited from training data remains a pressing concern. Prior investigations into bias in LLMs have focused on the association…

Research on the cognitive plausibility of language models (LMs) has so far mostly concentrated on modelling psycholinguistic response variables such as reading times, gaze durations and N400/P600 EEG signals, while mostly leaving out the…

Large Language Models (LLMs) have emerged as powerful generative Artificial Intelligence solutions which can be applied to several fields and areas of work. This paper presents results and reflection of an experiment done to use the model…

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only…

Large language models (LLMs) reflect societal norms and biases, especially about gender. While societal biases and stereotypes have been extensively researched in various NLP applications, there is a surprising gap for emotion analysis.…

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

In recent years, large language models (LLMs) have demonstrated strong performance on multilingual tasks. Given its wide range of applications, cross-cultural understanding capability is a crucial competency. However, existing benchmarks…

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn…

Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can…

SAEs have recently been employed as a promising unsupervised approach for understanding the representations of layers of Large Language Models (LLMs). However, with the growth in model size and complexity, training SAEs is computationally…

Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4. These LLM-based chatbots encode the potential biases while retaining disparities that…