相关论文: Steering Large Language Models for Machine Transla…

Incorporating personal preference is crucial in advanced machine translation tasks. Despite the recent advancement of machine translation, it remains a demanding task to properly reflect personal style. In this paper, we introduce a…

Model steering represents a powerful technique that dynamically aligns large language models (LLMs) with human preferences during inference. However, conventional model-steering methods rely heavily on externally annotated data, not only…

Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based…

Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space. This enables useful applications such as steering - influencing the output of a model towards a desired concept -…

Sparse autoencoders (SAEs) are a mechanistic interpretability technique that have been used to provide insight into learned concepts within large protein language models. Here, we employ TopK and Ordered SAEs to investigate autoregressive…

Large Language Models (LLMs) have demonstrated strong capabilities in rewriting text across various styles. However, effectively leveraging this ability for example-based arbitrary style transfer, where an input text is rewritten to match…

Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (e.g. backtracking, cross-verification) during reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are…

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…

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…

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the…

LLMs are deployed globally, yet produce responses biased towards cultures with abundant training data. Existing cultural localization approaches such as prompting or post-training alignment are black-box, hard to control, and do not reveal…

Steering vectors are a promising approach to control the behaviour of large language models. However, their underlying mechanisms remain poorly understood. While sparse autoencoders (SAEs) may offer a potential method to interpret steering…

Current evaluations of Large Language Model (LLM) steering techniques focus on task-specific performance, overlooking how well steered representations align with human cognition. Using a well-established triadic similarity judgment task, we…

Large Language Models (LLMs) demonstrate the ability to solve reasoning and mathematical problems using the Chain-of-Thought (CoT) technique. Expanding CoT length, as seen in models such as DeepSeek-R1, significantly enhances this reasoning…

As large language models (LLMs) improve in their capacity to serve as personal AI assistants, their ability to output uniquely tailored, personalized responses that align with the soft preferences of their users is essential for enhancing…

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…

Recent work shows that Sparse Autoencoders (SAE) applied to large language model (LLM) layers have neurons corresponding to interpretable concepts. These SAE neurons can be modified to align generated outputs, but only towards…

Effective and reliable control over large language model (LLM) behavior is a significant challenge. While activation steering methods, which add steering vectors to a model's hidden states, are a promising approach, existing techniques…

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…