Related papers: Controllable LLM Reasoning via Sparse Autoencoder-…

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the features learned by large language models (LLMs). By reconstructing features with sparsely activated networks, SAEs aim to recover complex superposed…

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…

Recent work shows that, beyond discrete reasoning through explicit chain-of-thought steps, which are limited by the boundaries of natural languages, large language models (LLMs) can also reason continuously in latent space, allowing richer…

The integration of slow-thinking mechanisms into large language models (LLMs) offers a promising way toward achieving Level 2 AGI Reasoners, as exemplified by systems like OpenAI's o1. However, several significant challenges remain,…

While Large Reasoning Models (LRMs) have achieved remarkable performance by scaling test-time compute, they frequently suffer from Cognitive Inertia, a failure pattern manifesting as either overthinking (inertia of motion) or reasoning…

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but…

LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forgetting associated with full fine-tuning. Sparse Autoencoders (SAEs) have emerged as a…

Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on reasoning traces to improve their reasoning abilities. However, how these methods shape…

Large language models have simplified the production of personalized translations reflecting predefined stylistic constraints. However, these systems still struggle when stylistic requirements are implicitly represented by a set of…

Recent advances in Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex tasks such as mathematics and coding. However, these models frequently exhibit a phenomenon known as overthinking during…

Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different levels of granularity and enable targeted steering of the…

Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rewards, where autoregressive decoding dominates time and…

Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model. However, prevailing gradient-based unlearning methods suffer from issues such as high computational costs, hyperparameter…

Recent advancements in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet their reliance on extensive manual labeling to provide procedural feedback remains a significant impediment. To address this…

Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a novel method for…

Sparse autoencoders (SAEs) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However, the sheer number of extracted directions makes comprehensive…

Altruism is fundamental to human societies, fostering cooperation and social cohesion. Recent studies suggest that large language models (LLMs) can display human-like prosocial behavior, but the internal computations that produce such…

We use sparse autoencoder (SAE) feature steering to amplify Dark Triad personality traits (Machiavellianism, narcissism, and psychopathy) in Llama-3.3-70B-Instruct and evaluate the resulting behavioral changes across five psychological…

Large Reasoning Models (LRMs) represent a breakthrough in AI problem-solving capabilities, but their effectiveness in interactive environments can be limited. This paper introduces and analyzes overthinking in LRMs. A phenomenon where…

Large language models (LLMs) demonstrate remarkable performance across diverse tasks, yet their effectiveness frequently depends on costly commercial APIs or cloud services. Model selection thus entails a critical trade-off between…