Related papers: Understanding Refusal in Language Models with Spar…
Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…
Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the…
Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…
Model internals encode rich information about how a large language model (LLM) processes its training data; however, post-training data engineering largely relies on external signals and ignores rich intrinsic signals lying in model…
Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…
Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…
Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compact causal mechanism for persuasion-induced factual errors. A…
The increasing integration of Large Language Models (LLMs) into society necessitates robust defenses against vulnerabilities from jailbreaking and adversarial prompts. This project proposes a recursive framework for enhancing the resistance…
We investigate the adversarial robustness of LLMs in transfer learning scenarios. Through comprehensive experiments on multiple datasets (MBIB Hate Speech, MBIB Political Bias, MBIB Gender Bias) and various model architectures (BERT,…
Large Language Models (LLMs) can produce surprisingly sophisticated estimates of their own uncertainty. However, it remains unclear to what extent this expressed confidence is tied to the reasoning, knowledge, or decision making of the…
The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…
Mitigating hallucinations in Large Language Models (LLMs) is critical for their reliable deployment. Existing methods typically fine-tune LLMs to abstain from answering questions beyond their knowledge scope. However, these methods often…
Modern text classification methods heavily rely on contextual embeddings from large language models (LLMs). Compared to human-engineered features, these embeddings provide automatic and effective representations for classification model…
We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate…
Large Language Models (LLMs) are known to exhibit social, demographic, and gender biases, often as a consequence of the data on which they are trained. In this work, we adopt a mechanistic interpretability approach to analyze how such…
While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety constraints. Existing strategies, ranging from heuristic prompt engineering to computationally…
Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…
Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…
Large language models (LLMs) have been widely deployed across numerous fields. Reinforcement Learning from Human Feedback (RLHF) leverages reward models (RMs) as proxies for human preferences to align LLM behaviors with human values, making…
The evaluation of large language models (LLMs) relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics for a given capability, but those aggregated metrics can obscure (i) particular sub-areas where the…