Evaluating Sycophancy in Chinese Large Language Models on Factual Questions Derived from Online Search Queries

3 days agoReported by arXiv23

Evaluating Sycophancy in Chinese Large Language Models on Factual Questions Derived from Online Search Queries. It centres on DeepSeek, and also names Qwen and Benchmarks. Reported by arXiv. Bharat Hunt files it under AI Models — the section covering a new or updated model, its capabilities, benchmarks or availability.

Written by Bharat Hunt from the headline and the coverage below. The original reporting is the source of truth.

Read original coverage

Companies, models and people in this story

Reported by arXiv

First seen 3 days ago

arXivEvaluating Sycophancy in Chinese Large Language Models on Factual Questions Derived from Online Search Queries3 days agoGeng Liu

AI Models24

Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency

Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency. It centres on Reasoning Models, and also names Inference and Fine-tuning. Reported by arXiv. Bharat Hunt files it under AI Models and AI Coding — the section covering a new or updated model, its capabilities, benchmarks or availability.

arXiv2 days ago

AI Coding23

FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation

← All AI stories

Evaluating Sycophancy in Chinese Large Language Models on Factual Questions Derived from Online Search Queries

Companies, models and people in this story

Reported by arXiv

Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency

FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation

Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers

SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving

Companies, models and people in this story

Reported by arXiv

Related AI coverage

Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency

FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation

Stale-Document Poisoning: When Outdated Retrieval Overrides Correct Model Answers

SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving