Open information extraction

The Consensus Trap: Dissecting Subjectivity and the “Ground Truth” Illusion in Data Annotation

As part of the Digital Library's transition to Open Access, new features for researchers are available in the Premium Edition. Click here to learn more.

Ambiguity, legibility, and working in the open – ambiguiti.es

Believe It or Not: How Deeply do LLMs Believe Implanted Facts?

Knowledge editing techniques promise to implant new factual knowledge into large language models (LLMs). But do LLMs really believe these facts? We develop a framework to measure belief depth and use it to evaluate the success of knowledge editing techniques. We operationalize belief depth as the extent to which implanted knowledge 1) generalizes to related contexts (e.g. Fermi estimates several logical steps removed), 2) is robust to self-scrutiny and direct challenge, and 3) is represented similarly to genuine knowledge (as measured by linear probes). Our evaluations show that simple prompting and mechanistic editing techniques fail to implant knowledge deeply. In contrast, Synthetic Document Finetuning (SDF) - where models are trained on LLM-generated documents consistent with a fact - often succeeds at implanting beliefs that behave similarly to genuine knowledge. However, SDF's success is not universal, as implanted beliefs that contradict basic world knowledge are brittle and representationally distinct from genuine knowledge. Overall, our work introduces measurable criteria for belief depth and enables the rigorous evaluation necessary for deploying knowledge editing in real-world applications.

Believe It or Not: How Deeply do LLMs Believe Implanted Facts?

Knowledge editing techniques promise to implant new factual knowledge into large language models (LLMs). But do LLMs really believe these facts? We develop a framework to measure belief depth and use it to evaluate the success of knowledge editing techniques. We operationalize belief depth as the extent to which implanted knowledge 1) generalizes to related contexts (e.g. Fermi estimates several logical steps removed), 2) is robust to self-scrutiny and direct challenge, and 3) is represented similarly to genuine knowledge (as measured by linear probes). Our evaluations show that simple prompting and mechanistic editing techniques fail to implant knowledge deeply. In contrast, Synthetic Document Finetuning (SDF) - where models are trained on LLM-generated documents consistent with a fact - often succeeds at implanting beliefs that behave similarly to genuine knowledge. However, SDF's success is not universal, as implanted beliefs that contradict basic world knowledge are brittle and representationally distinct from genuine knowledge. Overall, our work introduces measurable criteria for belief depth and enables the rigorous evaluation necessary for deploying knowledge editing in real-world applications.

Olmo from Ai2

Our fully open language model and complete model flow.

TheoremGraph: Bridging Formal and Informal Mathematics

Mathematical knowledge is organized around statements and their dependencies, but this structure is exposed unevenly: informal papers cite mostly at the document level, while formal libraries record fine-grained dependencies over a much smaller body of mathematics. We introduce TheoremGraph, a unified statement-level dependency graph spanning both informal and formal mathematics. On the informal side, we parse 11.7M theorem-like environments from mathematics arXiv and recover 18.3M candidate directed dependencies, each labeled by the extractor that proposed it so downstream users can trade coverage for precision. On the formal side, we release LeanGraph, a Lean 4 elaborator-level extractor producing 388,105 declaration nodes and 11.3M typed edges across 25 Lean projects. We bridge the two graphs by embedding generated natural-language slogans into a shared semantic space, linking related statements across papers and across the informal/formal divide; an LLM judge affirms 47,952 such matches above a 0.8 cosine floor, with the judge-acceptance rate rising from 48% across the floor to 87% in the >=0.9 tier. On formal concept retrieval, our name-and-signature representation with graph expansion comes within 0.5pp of LeanSearch v2's reranked Recall@10 (0.775 vs. 0.780) without an LM reranker. We release the dataset, extractors, HTTP API, and MCP interface as infrastructure for mathematical search, attribution, and retrieval-augmented reasoning, available at theoremsearch.com and huggingface.co/datasets/uw-math-ai/theorem-matching.

Wikipedia:Signs of AI writing

This is a list of writing and formatting conventions typical of AI chatbots such as ChatGPT, with real examples taken from Wikipedia articles, drafts, comments, and other content. It is a field guide to help detect undisclosed AI-generated content on Wikipedia: while some of the signs may be broadly applicable, some may not apply in a non-Wikipedia context.[a] Not all text featuring these indicators is AI-generated, as the large language models that power AI chatbots are trained on human writing, including Wikipedia. Many elements of AI writing can be found in editorials, blogs, or fan fiction.

Machine-readable attitudes - Computational Semantics++

User intent declarations can be viewed as propositional attitudes (permission, prohibition, desire, intention, belief, etc.) over structured descriptions of data use. Treating them that way gives you composable building blocks from existing theory and lens-based translations between community vocabularies that make explicit what each translation cannot carry through.

Argumentation theory | Communication and Mass Media | Research Starters | EBSCO Research

<p>Argumentation theory explores the processes and methods of reasoning and debate used by individuals in both formal and informal contexts. The theory has roots in ancient philosophical discourse, particularly from figures like Aristotle, and has evolved through the contributions of modern philosophers such as Chaïm Perelman and Stephen Toulmin. It highlights how arguments are structured, identifying key components such as claims, grounds (or data), and warrants, which collectively help participants make their case. </p> <p>Additionally, arguments can be categorized into three main types: factual claims, which are verifiable; judgment or value claims, which are subjective; and policy claims, which pertain to proposed courses of action. This framework acknowledges the influence of personal biases, often shaping the reasoning process, and emphasizes the importance of logical support, backing, qualifiers, and rebuttals in strengthening arguments. In academic contexts, the theory suggests that creating valid topics should focus on policy arguments, while also addressing counterarguments to foster a comprehensive debate. Overall, argumentation theory serves as a critical tool for understanding how reasoning and persuasive communication function in various scenarios.</p>

hijohnnylin/neuronpedia

open source interpretability platform 🧠

Unpacking Open Source Artificial Intelligence: Toward a Framework for Openness in Foundation Models

Openness has long driven innovation in software,9 and AI is no exception.12 While some see openness in foundation models (FMs) as a security threat,18 others argue that restricting access will not meaningfully reduce risk and will limit the benefits of transparency, research, and global participation.3 As the EU AI Act reporting requirements on FMs—also referred to as general-purpose AI models (GPAIMs)—move toward implementation, there is an urgent need for a more nuanced and informed understanding of openness in AI systems.

fastino-ai/GLiNER2

Unified Schema-Based Information Extraction