Almanac
model

Qwen 2.5-7B

modelactiveprovisionalqwen-2-5-7b-4c046071·2 events·first seen 29d ago

Aliases: Qwen 2.5-7B, Qwen 2.5

Co-occurring entities

More like this (12)

Recent events (2)

7arXiv · cs.AI·23d ago·source ↗

Geopolitical Bias in LLMs Originates in Post-Training, Not Pre-Training Data

A study testing seven open-weight LLM pairs (base vs. chat models) across seven labs finds that geopolitical bias is introduced during post-training rather than inherited from pre-training data. Six of seven labs showed post-training shifts favoring the developer's home country or region, with Alibaba's Qwen 2.5 showing the most extreme shift (18x increase in China-favourability log-odds). The effect is also language-dependent: Mistral becomes pro-France only under French prompting. The authors argue this implicates alignment and RLHF processes as active shapers of geopolitical perspective, calling for greater transparency and auditing of post-training pipelines.

5arXiv · cs.CL·29d ago·source ↗

DiSP: A Sample-and-Judge Framework for Efficient In-Context Learning Demonstration Selection

DiSP reframes ICL demonstration selection as a prediction problem rather than a search problem, arguing it is cheaper to judge whether a query-context pair will succeed than to find an optimal context. The framework stratifies queries by difficulty using a lightweight router, trains level-specific judges, and applies stop-on-acceptance judging under an explicit budget. Evaluated on five classification datasets with Llama 3-8B and Qwen 2.5-7B, DiSP improves over strong learned selection baselines by up to 3.4% accuracy while achieving up to 23x wall-clock speedup.