{"slug": "reach-into-the-choir-free-list-elicitation-uncovers-distinct-model-voices-in-llm", "title": "Reach Into The CHOIR: Free-List Elicitation Uncovers Distinct Model Voices in LLM Ensembles", "summary": "A new arXiv paper (2609.38448v1) introduces CHOIR (Collective Hierarchically-Ordered Inquiry Responses), a framework that adapts free-list elicitation from cognitive anthropology to LLM ensembles to distinguish genuine model diversity from surface-level homogeneity. Evaluated on Infinity-Chat 100, CHOIR reproduced high surface agreement with 93 of 100 prompts above chance while separating narrow prompts from broad prompts with recoverable depth, and found base-model identity remains the strongest recoverable signature, with persona prompts shifting surfaced concepts within base-model signatures. The framework includes a source-blind ranking module that prioritizes rare-but-stable candidates for later inspection.", "body_md": "arXiv:2609.38448v1 Announce Type: new \nAbstract: Open-ended LLM homogeneity can create false plurality when several systems appear to offer independent perspectives while returning the same familiar default. Single-pass answers obscure the distinction between agreement produced by a tightly constrained answer space, prompt-vocabulary echo, and broader answer spaces with stable alternatives beneath the surface. We introduce CHOIR (Collective Hierarchically-Ordered Inquiry Responses), a framework that adapts free-list elicitation from cognitive anthropology to LLM ensembles. CHOIR repeatedly elicits ranked lists, clusters items into prompt-level concepts, and measures concept salience across models, prompt variants, and persona conditions. We evaluate CHOIR on Infinity-Chat 100, an external prompt bank from recent work on open-ended model homogeneity, and on a 27-question targeted diagnostic bank designed to isolate mechanism-level contrasts. On Infinity-Chat 100, CHOIR reproduces high surface agreement (93/100 prompts above chance) while separating narrow prompts from broad prompts with recoverable depth. Across targeted probes and the external prompt bank, base-model identity remains the strongest recoverable signature, and persona prompts shift surfaced concepts within base-model signatures. A source-blind ranking module prioritises rare-but-stable candidates for later inspection. CHOIR turns open-ended homogeneity into a diagnostic measurement problem by asking where models converge, why they converge, and what remains reachable under structured depth probing.", "url": "https://wpnews.pro/news/reach-into-the-choir-free-list-elicitation-uncovers-distinct-model-voices-in-llm", "canonical_source": "https://arxiv.org/abs/2609.38448", "published_at": "2026-10-01 04:00:00+00:00", "updated_at": "2026-10-01 04:17:53.305868+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "machine-learning", "artificial-intelligence"], "entities": ["CHOIR", "Infinity-Chat 100", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/reach-into-the-choir-free-list-elicitation-uncovers-distinct-model-voices-in-llm", "markdown": "https://wpnews.pro/news/reach-into-the-choir-free-list-elicitation-uncovers-distinct-model-voices-in-llm.md", "text": "https://wpnews.pro/news/reach-into-the-choir-free-list-elicitation-uncovers-distinct-model-voices-in-llm.txt", "jsonld": "https://wpnews.pro/news/reach-into-the-choir-free-list-elicitation-uncovers-distinct-model-voices-in-llm.jsonld"}}