Related papers: AntiPaSTO: Self-Supervised Honesty Steering via An…

Self-supervised sentence representation learning is the task of constructing an embedding space for sentences without relying on human annotation efforts. One straightforward approach is to finetune a pretrained language model (PLM) with a…

In human-written articles, we often leverage the subtleties of text style, such as bold and italics, to guide the attention of readers. These textual emphases are vital for the readers to grasp the conveyed information. When interacting…

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead…

Large Language Models (LLMs) still produce gender-stereotyped language even in occupation-neutral contexts that reflect deep societal biases (Rudinger et al., 2018). To address this, prior work has proposed prompting, constrained decoding…

A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…

Though offering amazing contextualized token-level representations, current pre-trained language models take less attention on accurately acquiring sentence-level representation during their self-supervised pre-training. However,…

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…

Negation has been a long-standing challenge for language models. Previous studies have shown that they struggle with negation in many natural language understanding tasks. In this work, we propose a self-supervised method to make language…

Predictive models are being increasingly used to support consequential decision making at the individual level in contexts such as pretrial bail and loan approval. As a result, there is increasing social and legal pressure to provide…

Large Language Models (LLMs) are often aligned using contrastive alignment objectives and preference pair datasets. The interaction between model, paired data, and objective makes alignment a complicated procedure, sometimes producing…

Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless, it is unclear how improved representation learning can…

Steering vectors work for some concepts and layers but fail for others, and practitioners have no way to predict which setting applies before running an intervention. We introduce the Linear Accessibility Profile (LAP), a per-layer…

Large language models (LLMs) tend to verbalize confidence scores that are largely detached from their actual accuracy, yet the geometric relationship governing this behavior remain poorly understood. In this work, we present a mechanistic…

Multilingual representations pre-trained with monolingual data exhibit considerably unequal task performances across languages. Previous studies address this challenge with resource-intensive contextualized alignment, which assumes the…

Can freely moving humans or animals themselves serve as calibration targets for multi-camera systems while simultaneously estimating their correspondences across views? We humans can solve this problem by mentally rotating the observed 2D…

Large Language Models (LLMs) have shown impressive performance in natural language tasks, but their outputs can exhibit undesirable attributes or biases. Existing methods for steering LLMs toward desired attributes often assume unbiased…

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…

In self-supervised representation learning, Siamese networks are a natural architecture for learning transformation-invariance by bringing representations of positive pairs closer together. But it is prone to collapse into a degenerate…

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

3D pose transfer is a challenging generation task that aims to transfer the pose of a source geometry onto a target geometry with the target identity preserved. Many prior methods require keypoint annotations to find correspondence between…