Related papers: Depth-Wise Activation Steering for Honest Language…
Recent advances in Large Language Models (LLMs) - particularly model scaling and test-time techniques - have greatly enhanced the reasoning capabilities of language models at the expense of higher inference costs. To lower inference costs,…
We provide evidence that language models can detect, localize and, to a certain degree, verbalize the difference between perturbations applied to their activations. More precisely, we either (a) mask activations, simulating dropout, or (b)…
It is a critical challenge to efficiently unlock the powerful reasoning potential of Large Language Models (LLMs) for specific tasks or new distributions. Existing test-time adaptation methods often require tuning model parameters, which is…
Controlling undesirable Large Language Model (LLM) behaviors, such as the generation of unsafe content or failing to adhere to safety guidelines, often relies on costly fine-tuning. Activation steering provides an alternative for…
The memorization of training data by Large Language Models (LLMs) poses significant risks, including privacy leaks and the regurgitation of copyrighted content. Activation steering, a technique that directly intervenes in model activations,…
Large language models (LLMs) require alignment to effectively and safely follow user instructions. This process necessitates training an aligned version for every base model, resulting in significant computational overhead. In this work, we…
Large language models exhibit strong multilingual capabilities, yet significant performance gaps persist between dominant and non-dominant languages. Prior work attributes this gap to imbalances between shared and language-specific neurons…
In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise…
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…
The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…
Large language models (LLMs) demonstrate significant knowledge through their outputs, though it is often unclear whether false outputs are due to a lack of knowledge or dishonesty. In this paper, we investigate instructed dishonesty,…
The scaling of large language models (LLMs) emphasizes increasing depth, yet performance gains diminish with added layers. Prior work introduces the concept of "effective depth", arguing that deeper models fail to fully utilize their layers…
Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may…
Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data. This enables efficient adaptation to diverse downstream tasks. However, the lack of interpretability in their underlying mechanisms limits…
Controllable generation requires language models to realize output characteristics such as reading level, politeness, and toxicity. Existing steering methods are often indirect, require access to internal activations, or depend on auxiliary…
Large Language Models (LLMs) offer strong capabilities but incur high inference costs due to dense computation and memory access. Training-free activation sparsity is a promising approach for efficient LLM inference, yet existing methods…
Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effective, existing methods often apply a fixed steering strength to…
Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown that models encode linear representations of their own…
Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that…
Large language models (LLMs) often exhibit undesirable behaviours, such as generating untruthful or biased content. Editing their internal representations has been shown to be effective in mitigating such behaviours on top of the existing…