English
Related papers

Related papers: White-Box Sensitivity Auditing with Steering Vecto…

200 papers

We propose an auditing method to identify whether a large language model (LLM) encodes patterns such as hallucinations in its internal states, which may propagate to downstream tasks. We introduce a weakly supervised auditing technique…

Machine Learning · Computer Science 2023-12-06 Miriam Rateike , Celia Cintas , John Wamburu , Tanya Akumu , Skyler Speakman

Large Language Models (LLMs) have demonstrated remarkable abilities to solve problems requiring multiple reasoning steps, yet the internal mechanisms enabling such capabilities remain elusive. Unlike existing surveys that primarily focus on…

Computation and Language · Computer Science 2026-01-22 Liangming Pan , Jason Liang , Jiaran Ye , Minglai Yang , Xinyuan Lu , Fengbin Zhu

Hallucinations are a persistent problem with Large Language Models (LLMs). As these models become increasingly used in high-stakes domains, such as healthcare and finance, the need for effective hallucination detection is crucial. To this…

Computation and Language · Computer Science 2026-01-29 Dylan Bouchard , Mohit Singh Chauhan

Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechanisms responsible for attack success or failure. Conversely,…

Machine Learning · Computer Science 2025-05-07 Thomas Winninger , Boussad Addad , Katarzyna Kapusta

Lean processes focus on doing only necessery things in an efficient way. Artificial intelligence and Machine Learning offer new opportunities to optimizing processes. The presented approach demonstrates an improvement of the test process by…

Software Engineering · Computer Science 2019-06-10 Alexander Poth , Quirin Beck , Andreas Riel

Recent advances in generative AI have led to remarkable interest in using systems that rely on large language models (LLMs) for practical applications. However, meaningful evaluation of these systems in real-world scenarios comes with a…

Artificial Intelligence · Computer Science 2025-07-22 Ethan M. Rudd , Christopher Andrews , Philip Tully

Mitigating elderly loneliness requires policy interventions that achieve both adaptability and auditability. Existing methods struggle to reconcile these objectives: traditional agent-based models suffer from static rigidity, while direct…

Artificial Intelligence · Computer Science 2026-03-25 Shaoxin Zhong , Yuchen Su , Michael Witbrock

Large Language Models (LLMs) are being adopted across a wide range of tasks, including decision-making processes in industries where bias in AI systems is a significant concern. Recent research indicates that LLMs can harbor implicit biases…

Computation and Language · Computer Science 2024-10-18 Divyanshu Kumar , Umang Jain , Sahil Agarwal , Prashanth Harshangi

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

Machine Learning · Computer Science 2025-02-11 Brian Formento , Chuan Sheng Foo , See-Kiong Ng

Large language models (LLMs) are increasingly embedded in consequential decisions across healthcare, finance, employment, and public services. Yet accountability remains fragile because process transparency is rarely recorded in a durable…

Computers and Society · Computer Science 2026-01-29 Victor Ojewale , Harini Suresh , Suresh Venkatasubramanian

Large Language Models (LLMs) frequently generate plausible but non-factual content, a phenomenon known as hallucination. While existing detection methods typically rely on computationally expensive sampling-based consistency checks or…

Machine Learning · Computer Science 2026-05-07 Dan Wilson , Mohamed Akrout

Methods for adapting language models (LMs) to new tasks and domains have traditionally assumed white-box access to the model, and work by modifying its parameters. However, this is incompatible with a recent trend in the field, where the…

Computation and Language · Computer Science 2023-05-29 Aitor Ormazabal , Mikel Artetxe , Eneko Agirre

Language models can distinguish between testing and deployment phases -- a capability known as evaluation awareness. This has significant safety and policy implications, potentially undermining the reliability of evaluations that are…

Computation and Language · Computer Science 2025-07-10 Jord Nguyen , Khiem Hoang , Carlo Leonardo Attubato , Felix Hofstätter

Large Language Models (LLM) have made significant advances in the recent past becoming more mainstream in Artificial Intelligence (AI) enabled human-facing applications. However, LLMs often generate stereotypical output inherited from…

Computation and Language · Computer Science 2023-11-27 Wu Zekun , Sahan Bulathwela , Adriano Soares Koshiyama

AI tools to support real world decision making must be able to build simulation models that inform their recommendations and render them interpretable. Tools that can automate aspects of modeling practice must complement human expertise,…

Artificial Intelligence · Computer Science 2026-05-29 Sara Metcalf , William Schoenberg

Commercial large language models are typically deployed as black-box API services, requiring users to trust providers to execute inference correctly and report token usage honestly. We present IMMACULATE, a practical auditing framework that…

Cryptography and Security · Computer Science 2026-02-27 Yanpei Guo , Wenjie Qu , Linyu Wu , Shengfang Zhai , Lionel Z. Wang , Ming Xu , Yue Liu , Binhang Yuan , Dawn Song , Jiaheng Zhang

Large language models (LLMs) are widely used as scalable evaluators of model responses in lieu of human annotators. However, imperfect sensitivity and specificity of the LLM judges induce bias in naive evaluation scores. We propose a simple…

Machine Learning · Computer Science 2026-02-10 Chungpa Lee , Thomas Zeng , Jongwon Jeong , Jy-yong Sohn , Kangwook Lee

In this paper, we present a novel black-box online controller that uses only end-to-end measurements over short segments, without internal instrumentation, and hill climbing to maximize goodput, defined as the throughput of requests that…

Artificial Intelligence · Computer Science 2026-03-13 Yonas Atinafu , Henry Lin , Robin Cohen

Large Language models (LLMs) can generate complicated source code from natural language prompts. However, LLMs can generate output that deviates from what the user wants, requiring supervision and editing. To support this process, we offer…

Software Engineering · Computer Science 2026-01-01 David Gros , Prem Devanbu

It is increasingly important to evaluate how text generation systems based on large language models (LLMs) behave, such as their tendency to produce harmful output or their sensitivity to adversarial inputs. Such evaluations often rely on a…

Computation and Language · Computer Science 2025-11-17 Rachel Longjohn , Shang Wu , Saatvik Kher , Catarina Belém , Padhraic Smyth