Corpus Christi: Establishing Replicability when Sharing the Bread is Not Allowed

• URL: http://arxiv.org/abs/2404.11977v1
• Date: Thu, 18 Apr 2024 08:14:40 GMT
• Title: Corpus Christi: Establishing Replicability when Sharing the Bread is Not Allowed
• Authors: René Helmke, Elmar Padilla, Nils Aschenbruck,
• Abstract summary: We identify binary analysis challenges that significantly impact corpus creation. We use them to derive a framework of key corpus requirements that nurture the scientific goals of replicability and representativeness. We apply the framework to 44 top tier papers and collect 704 data points to show that there is currently no common ground on corpus creation.
• Score: 1.1101390076342181
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this paper, we provide practical tools to improve the scientific soundness of firmware corpora beyond the state of the art. We identify binary analysis challenges that significantly impact corpus creation. We use them to derive a framework of key corpus requirements that nurture the scientific goals of replicability and representativeness. We apply the framework to 44 top tier papers and collect 704 data points to show that there is currently no common ground on corpus creation. We discover in otherwise excellent work, that incomplete documentation and inflated corpus sizes blur visions on representativeness and hinder replicability. Our results show that the strict framework provides useful and practical guidelines that can identify miniscule step stones in corpus creation with significant impact on soundness. Finally, we show that it is possible to meet all requirements: We provide a new corpus called LFwC. It is designed for large-scale static analyses on Linux-based firmware and consists of 10,913 high-quality images, covering 2,365 network appliances. We share rich meta data and scripts for replicability with the community. We verify unpacking, perform deduplication, identify contents, and provide bug ground truth. We identify ISAs and Linux kernels. All samples can be unpacked with the open source tool FACT.

Related papers

• Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
  We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
  arXiv  Detail & Related papers  (2025-06-29T08:34:59Z)
• Illusions of Relevance: Using Content Injection Attacks to Deceive Retrievers, Rerankers, and LLM Judges [52.96987928118327]
  We find that embedding models for retrieval, rerankers, and large language model (LLM) relevance judges are vulnerable to content injection attacks. We identify two primary threats: (1) inserting unrelated or harmful content within passages that still appear deceptively "relevant", and (2) inserting entire queries or key query terms into passages to boost their perceived relevance. Our study systematically examines the factors that influence an attack's success, such as the placement of injected content and the balance between relevant and non-relevant material.
  arXiv  Detail & Related papers  (2025-01-30T18:02:15Z)
• Corpus-informed Retrieval Augmented Generation of Clarifying Questions [23.123116796159717]
  This study aims to develop models that generate corpus informed clarifying questions for web search. In current datasets search intents are largely unsupported by the corpus, which is problematic both for training and evaluation. We propose dataset augmentation methods that align the ground truth clarifications with the retrieval corpus.
  arXiv  Detail & Related papers  (2024-09-27T09:20:42Z)
• What Evidence Do Language Models Find Convincing? [94.90663008214918]
  We build a dataset that pairs controversial queries with a series of real-world evidence documents that contain different facts. We use this dataset to perform sensitivity and counterfactual analyses to explore which text features most affect LLM predictions. Overall, we find that current models rely heavily on the relevance of a website to the query, while largely ignoring stylistic features that humans find important.
  arXiv  Detail & Related papers  (2024-02-19T02:15:34Z)
• Alignment for Honesty [105.72465407518325]
  Recent research has made significant strides in aligning large language models (LLMs) with helpfulness and harmlessness. In this paper, we argue for the importance of alignment for emphhonesty, ensuring that LLMs proactively refuse to answer questions when they lack knowledge. We address these challenges by first establishing a precise problem definition and defining honesty'' inspired by the Analects of Confucius.
  arXiv  Detail & Related papers  (2023-12-12T06:10:42Z)
• What's In My Big Data? [67.04525616289949]
  We propose What's In My Big Data? (WIMBD), a platform and a set of sixteen analyses that allow us to reveal and compare the contents of large text corpora. WIMBD builds on two basic capabilities -- count and search -- at scale, which allows us to analyze more than 35 terabytes on a standard compute node. Our analysis uncovers several surprising and previously undocumented findings about these corpora, including the high prevalence of duplicate, synthetic, and low-quality content.
  arXiv  Detail & Related papers  (2023-10-31T17:59:38Z)
• A Discrepancy Aware Framework for Robust Anomaly Detection [51.710249807397695]
  We present a Discrepancy Aware Framework (DAF), which demonstrates robust performance consistently with simple and cheap strategies. Our method leverages an appearance-agnostic cue to guide the decoder in identifying defects, thereby alleviating its reliance on synthetic appearance. Under the simple synthesis strategies, it outperforms existing methods by a large margin. Furthermore, it also achieves the state-of-the-art localization performance.
  arXiv  Detail & Related papers  (2023-10-11T15:21:40Z)
• Improving the Robustness of Summarization Systems with Dual Augmentation [68.53139002203118]
  A robust summarization system should be able to capture the gist of the document, regardless of the specific word choices or noise in the input. We first explore the summarization models' robustness against perturbations including word-level synonym substitution and noise. We propose a SummAttacker, which is an efficient approach to generating adversarial samples based on language models.
  arXiv  Detail & Related papers  (2023-06-01T19:04:17Z)
• Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise [14.38859858538404]
  In a retrieved document set, even the "relevant" documents may contain misleading or incorrect information. Our work investigates a more challenging scenario in which even the "relevant" documents may contain misleading or incorrect information. We propose approaches for handling knowledge conflicts among retrieved documents by explicitly fine-tuning a discriminator or prompting GPT-3.5 to elicit its discriminative capability.
  arXiv  Detail & Related papers  (2023-05-02T16:28:10Z)
• Unsupervised Opinion Summarization with Noising and Denoising [85.49169453434554]
  We create a synthetic dataset from a corpus of user reviews by sampling a review, pretending it is a summary, and generating noisy versions thereof. At test time, the model accepts genuine reviews and generates a summary containing salient opinions, treating those that do not reach consensus as noise.
  arXiv  Detail & Related papers  (2020-04-21T16:54:57Z)
• Know thy corpus! Robust methods for digital curation of Web corpora [0.0]
  This paper proposes a novel framework for digital curation of Web corpora. It provides robust estimation of their parameters, such as their composition and the lexicon.
  arXiv  Detail & Related papers  (2020-03-13T17:21:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.