相关论文: LangFIR: Discovering Sparse Language-Specific Feat…

Pathology plays an important role in disease diagnosis, treatment decision-making and drug development. Previous works on interpretability for machine learning models on pathology images have revolved around methods such as attention value…

Code-switching (CS) phenomenon occurs when words or phrases from different languages are alternated in a single sentence. Due to data scarcity, building an effective CS Automatic Speech Recognition (ASR) system remains challenging. In this…

Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of…

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…

Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, , i.e.,~manipulating internal representations during inference, has emerged…

Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language models map multilingual content into English-aligned representations at…

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting language model activations by decomposing them into sparse, interpretable features. A popular approach is the TopK SAE, that uses a fixed number of the most active…

Large language models (LLMs) have been widely deployed across numerous fields. Reinforcement Learning from Human Feedback (RLHF) leverages reward models (RMs) as proxies for human preferences to align LLM behaviors with human values, making…

Self-destructive behaviors are linked to complex psychological states and can be challenging to diagnose. These behaviors may be even harder to identify within subcultural groups due to their unique expressions. As large language models…

We develop the sparse VAE for unsupervised representation learning on high-dimensional data. The sparse VAE learns a set of latent factors (representations) which summarize the associations in the observed data features. The underlying…

Automatic speech recognition (ASR) models rely on high-quality transcribed data for effective training. Generating pseudo-labels for large unlabeled audio datasets often relies on complex pipelines that combine multiple ASR outputs through…

To control the behavior of language models, steering methods attempt to ensure that outputs of the model satisfy specific pre-defined properties. Adding steering vectors to the model is a promising method of model control that is easier…

Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these models to improve downstream performance often degrades robustness against distribution…

Large language models often produce human-like moral judgments, but it is unclear whether this reflects an internal conceptual structure or superficial ``moral mimicry.'' Using Moral Foundations Theory (MFT) as an analytic framework, we…

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and…

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…

Sparse autoencoders (SAEs) model the activations of a neural network as linear combinations of sparsely occurring directions of variation (latents). The ability of SAEs to reconstruct activations follows scaling laws w.r.t. the number of…

Multimodal Large Language Models (MLLMs) are commonly derived by extending pre-trained Large Language Models (LLMs) with visual capabilities. In this work, we investigate how MLLMs process visual inputs by analyzing their attention…

Language identification (LID) recognizes the language of a spoken utterance automatically. According to recent studies, LID models trained with an automatic speech recognition (ASR) task perform better than those trained with a LID task…

Error slice discovery is crucial to diagnose and mitigate model errors. Current clustering or discrete attribute-based slice discovery methods face key limitations: 1) clustering results in incoherent slices, while assigning discrete…