llm-analysis

Tag

Cards List
#llm-analysis

Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities

arXiv cs.CL · 2026-05-26 Cached

This paper uses a pre-trained LLM with zero-shot classification to analyze approximately 20 million Twitch chat messages across seven game genres, finding that 2.4% of messages are toxic, with MOBA games having the highest rate (3.2%) and sports games the lowest (2%). The study also identifies significant differences in toxicity distributions across individual games within the same genre.

0 favorites 0 likes
#llm-analysis

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models

arXiv cs.CL · 2026-05-13 Cached

This article introduces Qwen-Scope, a toolkit of Sparse Autoencoders (SAEs) trained on Qwen3 and Qwen3.5 models to enable mechanistic analysis and intervention. It releases 14 groups of SAE weights covering dense and MoE backbones, providing sparse representations for residual-stream activations.

0 favorites 0 likes
#llm-analysis

More Aligned, Less Diverse? Analyzing the Grammar and Lexicon of Two Generations of LLMs

arXiv cs.CL · 2026-05-08 Cached

This academic paper analyzes the syntactic and lexical diversity of two generations of LLMs compared to human-authored news text, finding that newer, aligned models exhibit reduced diversity.

0 favorites 0 likes
#llm-analysis

Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior

Google DeepMind Blog · 2025-12-16 Cached

DeepMind releases Gemma Scope 2, an open suite of interpretability tools for the Gemma 3 model family, aiming to help the AI safety community understand and debug complex language model behaviors like hallucinations and jailbreaks.

0 favorites 0 likes
← Back to home

Submit Feedback