LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by a one-dimensional subspace, i.e., a refusal direction. In this work, we identify a new dimension to analyze safety mechanisms in LLMs, i.e., harmfulness, which is encoded internally as a separate concept from refusal. And there exists a harmfulness direction that is distinct from the refusal direction. As causal evidence, steering along the harmfulness direction can lead LLMs to interpret harmless instructions as harmful, but steering along the refusal direction tends to elicit refusal responses directly without reversing the model's judgment on harmfulness. Furthermore, using our identified harmfulness concept, we find that certain jailbreak methods work by reducing the refusal signals without suppressing the model's internal belief of harmfulness.

Due to the size and complexity of modern large language models (LLMs), it has proven challenging to uncover the underlying mechanisms that models use to solve reasoning problems. For instance, is their reasoning for a specific problem localized to certain parts of the network? Do they break down the reasoning problem into modular components that are then executed as sequential steps as we go deeper in the model? To better understand the reasoning capability of LLMs, we study a minimal propositional logic problem that requires combining multiple facts to arrive at a solution. By studying this problem on Mistral and Gemma models, up to 27B parameters, we illuminate the core components the models use to solve such logic problems. From a mechanistic interpretability point of view, we use causal mediation analysis to uncover the pathways and components of the LLMs' reasoning processes. Then, we offer fine-grained insights into the functions of attention heads in different layers. We not only find a sparse circuit that computes the answer, but we decompose it into sub-circuits that have four distinct and modular uses. Finally, we reveal that three distinct models - Mistral-7B, Gemma2-9B and Gemma-2-27B - contain analogous but not identical mechanisms.

Image Auto-regressive (AR) models have emerged as a powerful paradigm of visual generative models. Despite their promising performance, they suffer from slow generation speed due to the large number of sampling steps required. Although Distilled Decoding 1 (DD1) was recently proposed to enable few-step sampling for image AR models, it still incurs significant performance degradation in the one-step setting, and relies on a pre-defined mapping that limits its flexibility. In this work, we propose a new method, Distilled Decoding 2 (DD2), to further advances the feasibility of one-step sampling for image AR models. Unlike DD1, DD2 does not without rely on a pre-defined mapping.

We show how to "compile" human-readable programs into standard decoder-only transformer models.

Training vision language models (VLMs) aims to align visual representations from a vision encoder with the textual representations of a pretrained large language model (LLM). However, many VLMs exhibit reduced factual recall performance compared to their LLM backbones, raising the question of how effective multimodal fine-tuning is at extending existing mechanisms within the LLM to visual inputs. We argue that factual recall based on visual inputs requires VLMs to solve a two-hop problem: (1) forming entity representations from visual inputs, and (2) recalling associated factual knowledge based on these entity representations. By benchmarking 14 VLMs with various architectures (LLaVA, Native, Cross-Attention), sizes (7B-124B parameters), and training setups on factual recall tasks against their original LLM backbone models, we find that 11 of 14 models exhibit factual recall degradation. We select three models with high and two models with low performance degradation, and use attribution patching, activation patching, and probing to show that degraded VLMs struggle to use the existing factual recall circuit of their LLM backbone, because they resolve the first hop too late in the computation. In contrast, high-performing VLMs resolve entity representations early enough to reuse the existing factual recall mechanism. Finally, we demonstrate two methods to recover performance: patching entity representations from the LLM backbone into the VLM, and prompting with chain-of-thought reasoning. Our results highlight that the speed of early entity resolution critically determines how effective VLMs are in using preexisting LLM mechanisms. More broadly, our work illustrates how mechanistic analysis can explain and unveil systematic failures in multimodal alignment.

W e present Spanning Tree Autoregressive (STAR) modeling, which can incorporate prior knowledge of images, such as center bias and locality, to maintain sampling performance while also providing sufficiently flexible sequence orders to accommodate image editing at inference. Approaches that expose randomly permuted sequence orders to conventional autoregressive (AR) models in visual generation for bidirectional context either suffer from a decline in performance or compromise the flexibility in sequence order choice at inference. Instead, STAR utilizes traversal orders of uniform spanning trees sampled in a lattice defined by the positions of image patches. Traversal orders are obtained through breadth-first search, allowing us to efficiently construct a spanning tree whose traversal order ensures that the connected partial observation of the image appears as a prefix in the sequence through rejection sampling. Through the tailored yet structured randomized strategy compared to random permutation, STAR preserves the capability of postfix completion while maintaining sampling performance without any significant changes to the model architecture widely adopted in the language AR modeling.

Large Language Models (LLMs) demonstrate increasing conversational fluency, yet instilling them with nuanced, human-like emotional expression remains a significant challenge. Current alignment techniques often address surface-level output or require extensive fine-tuning. This paper demonstrates that targeted activation engineering can steer LLaMA 3.1-8B to exhibit more human-like emotional nuances. We first employ attribution patching to identify causally influential components, to find a key intervention locus by observing activation patterns during diagnostic conversational tasks. We then derive emotional expression vectors from the difference in the activations generated by contrastive text pairs (positive vs. negative examples of target emotions). Applying these vectors to new conversational prompts significantly enhances emotional characteristics: steered responses show increased positive sentiment (e.g., joy, trust) and more frequent first-person pronoun usage, indicative of greater personal engagement. Our findings offer a precise and interpretable framework and new directions for the study of conversational AI.

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training creates signal decay, leading to incomplete safety learning where safety training fails to transform model preferences in later response regions fully. We introduce base-favored tokens -- vocabulary elements where base models assign higher probability than aligned models -- as computational indicators of incomplete safety learning and develop a targeted completion method that addresses undertrained regions through adaptive penalties and hybrid teacher distillation. Experimental evaluation across Llama and Qwen model families demonstrates dramatic improvements in adversarial robustness, with 48--98% reductions in attack success rates while preserving general capabilities. These results establish both a mechanistic understanding and practical solutions for fundamental limitations in safety alignment methodologies.