mlsanityData to 7 Oct 2026

EdgeJury: Cross-Reviewed Small-Model Ensembles for Truthful Question Answering on Serverless Edge Inference

arXiv 2601.00850 ↗First posted 29 Dec 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Hallucinations hinder reliable question answering, especially in resource-constrained deployments where frontier-scale models or retrieval pipelines may be impractical. We present EdgeJury, a lightweight ensemble framework that improves truthfulness and robustness using only small instruction-tuned language models (3B-8B) suitable for serverless edge inference. EdgeJury orchestrates four stages: (1) parallel role-specialized generation, (2) anonymized cross-review with structured critiques and rankings, (3) chairman synthesis that integrates the strongest content while addressing flagged issues, and (4) claim-level consistency labeling based on inter-model agreement. On TruthfulQA (MC1), EdgeJury achieves 76.2% accuracy (95% CI: 72.8-79.6%), a +21.4% relative improvement over a single 8B baseline (62.8%), and outperforms standard baselines including self-consistency and majority voting under transparent compute accounting (total tokens and platform cost reported). On a 200-question adversarial EdgeCases set, EdgeJury yields +48.2% relative gains (95% CI: 44.0-52.4%). Manual analysis on 100 incorrect answers shows an approximately 55% reduction in factual hallucination errors versus the single-model baseline. Deployed on Cloudflare Workers AI, EdgeJury achieves 8.4 s median end-to-end latency, demonstrating that coordinated small-model ensembles can improve truthfulness on misconception-heavy QA benchmarks without external retrieval or proprietary large-model APIs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 43 references that are in the map. First posted on arXiv 29 Dec 2025.

Builds on

23 of 43 references.

References · 23

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  9. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  10. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  11. 2023Mistral 7Bcited by 3,065
  12. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
11 more
  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  4. 2024A Survey on LLM-as-a-Judgecited by 1,384
  5. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  6. 2023Textbooks Are All You Needcited by 561
  7. 2018AI safety via debatecited by 384
  8. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  9. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  10. 2023Inverse Scaling: When Bigger Isn't Bettercited by 205
  11. 2025The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake Newscited by 29

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024GRATH: Gradual Self-Truthifying for Large Language Models
  2. 2025Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground Truth
  3. 2026TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models
  4. 2025Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning
  5. 2026Vision-Language Model Confidence Is Not a Property of the Answer
  6. 2025EAGER: Edge-Aligned LLM Defense for Robust, Efficient, and Accurate Cybersecurity Question Answering
  7. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
  8. 2025Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering