LIVE PULSE
4.0 Anthropic CEO Amodei calls for slower AI development and shared safety rules — 11 src2.2 Agility Robotics unveils Digit 5 humanoid for warehouses and factories — 2 src2.0 Apple ships rebuilt Siri with Google Gemini, but not in the EU — 2 src1.8 Siri AI in macOS 27 Golden Gate: FAQ, Germany availability, privacy questions — 2 src1.4 Sam Altman says OpenAI will not go public in 2026, citing AI safety concerns — 5 src1.1 OpenAI contractors review real ChatGPT conversations to rate responses, report says — 2 src1.1 Anthropic data retention policy prompts firms to limit Claude use for sensitive work — 1 src1.1 Study examines issue bias in LLMs used as writing assistants before Swedish 2026 election — 1 src1.1 Study Audits Misalignment in Multi-Modal World Models — 1 src1.1 Retrieval-Grounded Reasoning Approach Proposed for Universal Multimodal Embeddings — 1 src4.0 Anthropic CEO Amodei calls for slower AI development and shared safety rules — 11 src2.2 Agility Robotics unveils Digit 5 humanoid for warehouses and factories — 2 src2.0 Apple ships rebuilt Siri with Google Gemini, but not in the EU — 2 src1.8 Siri AI in macOS 27 Golden Gate: FAQ, Germany availability, privacy questions — 2 src1.4 Sam Altman says OpenAI will not go public in 2026, citing AI safety concerns — 5 src1.1 OpenAI contractors review real ChatGPT conversations to rate responses, report says — 2 src1.1 Anthropic data retention policy prompts firms to limit Claude use for sensitive work — 1 src1.1 Study examines issue bias in LLMs used as writing assistants before Swedish 2026 election — 1 src1.1 Study Audits Misalignment in Multi-Modal World Models — 1 src1.1 Retrieval-Grounded Reasoning Approach Proposed for Universal Multimodal Embeddings — 1 src
HEATPULSEAI MAGAZINES
FLIP · FOLLOW · SAVE
Log inSign up

entity linking

topic3 events
papersSEP 12 04:00 UTC

Multi-Negative DPO Approach Proposed for Historical Entity Linking with LLMs

A new arXiv paper argues that preference optimization for historical entity linking is typically limited to a single negative candidate per training example, which throws away useful comparative information. The authors propose a multi-negative direct preference optimization method designed for LLM-based linking of entities in historical texts. The work is a replacement submission on arXiv's cs.AI listing.

llm/entity-linking/preference-optimization/nlp
papersSEP 10 04:00 UTC

Research Paper Addresses Query Brand Entity Linking for E-Commerce Search

A new version of an arXiv paper (2502.01555) explores how to connect short user search queries with the correct brand entities during e-commerce product retrieval. The authors highlight the difficulty of the task, since queries average only three to four words and lack grammatical structure. The work is cross-listed in the cs.AI and cs.LG categories.

e-commerce/search/entity-linking/nlp
papersSEP 10 04:00 UTC

New arXiv Paper Presents Joint Argument-Entity Detection in Political Debates

A new preprint introduces a joint approach to detecting and classifying both arguments and the entities they involve in political debate texts. The authors argue that claims and premises are hard to interpret on their own, so linking them to relevant entities makes argument mining outputs more meaningful. The work appears on arXiv's Computation and Language category.

nlp/argument-mining/political-debates/research