Searcharxiv⌕ Search

arXiv subjects

Anna Wu

Publications and source records attributed to Anna Wu.

5 recordsLinked to original sources

MicroLens: Read, Trace, and Rewire the Residual Stream with Two Lenses

Lenses that decode hidden states into words are a popular way to look inside language models, but a heatmap of decoded words only shows what a vector reads as and cannot distinguish whether, or how much, the model uses the information. We present an interactive viewer that puts reading, tracing and editing on the same layers-by-tokens grid of the residual stream. In the viewer, every cell can be decoded with two lenses, the logit lens and the Jacobian lens (J-lens), traced back to the tokens it drew from, and edited, with the rest of the model rerun on the spot. We demonstrate three usage scenarios on Gemma-3-4B-it, backed by sweeps over a few hundred prompts, to show what this tool can discover. First, the two lenses give different directions to write with, each suiting a different edit: the logit lens's word direction sets what a token outputs, while the J-lens's direction changes what later tokens read. Second, in two-hop trivia questions (the capital of the state or country containing a given city), the state or country is readable at the city token from as early as layer 7, and swapping it there can redirect the answer 92-98% of the time; however, at the answer position, the state or country information is not used. Third, when a chat model answers questions with a step-by-step reasoning prompt, the correct answer is often already the top word in the residual stream before any reasoning is written: for 89-92% of retrieval questions and 39-63% of multi-hop and serial ones, far above their respective distractors (at most 5%). However, ordering puzzles are an exception, as the model works them out only once it writes its final reasoning steps. Furthermore, for answers that are visible in the residual stream, the J-lens reads them a layer or two earlier than the logit lens across the different types of question.

cs.LG↗

Automatic, Real-time Classification of User Feedback Using Large Language Models

In this paper we discuss an ongoing multi-year project that aims to make open text feedback more accessible and useful to UX practitioners by automating classification and providing real time access to comments, themes, and analysis. By significantly lowering the time and knowledge cost of implementing automated solutions, we aim to effectively democratize our data analysis processes, allowing and encouraging non-technical stakeholders to access and leverage data on their own. We share both the organizational and technical constraints we have encountered over the course of this project, and the solutions we have prototyped as a result of those constraints.

cs.HC↗

Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing

We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals alongside six existing AI agents and ARTEMIS, our new agent scaffold, on a large university network consisting of ~8,000 hosts across 12 subnets. ARTEMIS is a multi-agent framework featuring dynamic prompt generation, arbitrary sub-agents, and automatic vulnerability triaging. In our comparative study, ARTEMIS placed second overall, discovering 9 valid vulnerabilities with an 82% valid submission rate and outperforming 9 of 10 human participants. While existing scaffolds such as Codex and CyAgent underperformed relative to most human participants, ARTEMIS demonstrated technical sophistication and submission quality comparable to the strongest participants. We observe that AI agents offer advantages in systematic enumeration, parallel exploitation, and cost -- certain ARTEMIS variants cost $18/hour versus $60/hour for professional penetration testers. We also identify key capability gaps: AI agents exhibit higher false-positive rates and struggle with GUI-based tasks.

cs.AI↗

Graph-Based Uncertainty-Aware Self-Training with Stochastic Node Labeling

Self-training has become a popular semi-supervised learning technique for leveraging unlabeled data. However, the over-confidence of pseudo-labels remains a key challenge. In this paper, we propose a novel \emph{graph-based uncertainty-aware self-training} (GUST) framework to combat over-confidence in node classification. Drawing inspiration from the uncertainty integration idea introduced by Wang \emph{et al.}~\cite{wang2024uncertainty}, our method largely diverges from previous self-training approaches by focusing on \emph{stochastic node labeling} grounded in the graph topology. Specifically, we deploy a Bayesian-inspired module to estimate node-level uncertainty, incorporate these estimates into the pseudo-label generation process via an expectation-maximization (EM)-like step, and iteratively update both node embeddings and adjacency-based transformations. Experimental results on several benchmark graph datasets demonstrate that our GUST framework achieves state-of-the-art performance, especially in settings where labeled data is extremely sparse.

cs.LG↗

Case Study for Developing a UXR Point of View for FinOps Product Innovation

In the dynamic landscape of Cloud financial management, we are sharing a case study exploring the development of a User Experience Research (UXR) Point of View (PoV) to drive FinOps product innovation. We demonstrate how qualitative and quantitative research methods working together to navigate the challenges of understanding customer needs, aligning cross-functional teams, and prioritizing limited resources. Through a multi-phased research approach, the research team identifies opportunities, quantifies pain points, and segments diverse customer cohorts. This culminated in a UXR PoV that informed the creation of a differentiated product strategy, a 'one-stop shop' dashboard empowering FinOps practitioners with actionable insights and tools. This case study highlights the power of mixed-methods research in uncovering actionable insights that drive impactful product innovation.

cs.HC↗