Research map / Large language models / AI and society
Certified Trustworthiness in the Era of Large Language Models
Linyi Li
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Position/survey-style paper on certified (provable) trustworthiness evaluation of deep learning and large language model systems, covering robustness, fairness, and numerical reliability.
Problem
Lack of trustworthiness (robustness, fairness, numerical reliability) of deep learning systems raises concerns in safety-critical settings, and existing evaluations are not rigorous or accurate enough to certify trustworthiness.
Approach
Argues for certified (provable, formally guaranteed) trustworthiness evaluation as a rigorous alternative to empirical testing, extended to the era of large language models. Full text was unavailable, so the specific method details are not stated in the abstract.
Closest papers by meaning
- Position: TrustLLM: Trustworthiness in Large Language Models (ICML 2024 · similarity 0.91)
- Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression (ICML 2024 · similarity 0.89)
- Towards Trustworthy Deep Learning (AAAI 2024 · similarity 0.88)
- U-trustworthy Models. Reliability, Competence, and Confidence in Decision-Making (AAAI 2024 · similarity 0.87)
- MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models (NeurIPS 2024 · similarity 0.87)
- Trustworthy Machine Learning through Data-Specific Indistinguishability (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
