garamp_qwen25_72b — Question Generation Task

Is this run manual or automatic?: automatic
Is this run based on the provided starter kit?: no
Briefly describe this run: Same structured pipeline with Qwen2.5-72B-Instruct: generate ~30 candidates/topic, apply cleaning (≤300 chars, single question, English, no compound), then choose 10 using TF-IDF MMR (α=0.7). Seed=42.
What other datasets or services (e.g. Google/Bing web search, ChatGPT, Perplexity, etc.) were used in producing the run?: None. Local execution with HF Transformers and scikit-learn.
Briefly describe LLMs used for this run (optional): Large instruction-tuned LLM (72B). Decoding: temperature=0.4, top_p=0.85, do_sample=True, no_repeat_ngram_size=4, repetition_penalty=1.1. TF-IDF + MMR (α=0.7). No finetuning.
Please give this run a priority for inclusion in manual assessments.: 4