arXiv cs.AI· Sebastian Cochinescu·· 2 天前AI 评分26
让 AI 可信的真相：将表达疑虑、来源溯源与信念修正作为可工程化的立场
Truth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance
AI 导读
研究测试了在固定语言模型上以行为层实现表达不确定性、来源感知断言与显式信念修正，并在合成模型与 Qwen2.5-0.5B-Instruct 上评估。
正文 · 原文
Abstract:Conversational agents often express answers in a uniformly confident register. We test whether expressed uncertainty, provenance-aware assertion, and explicit belief revision can be implemented as a behavior layer over a fixed language model; we do not test believability or trust. The layer combines three epistemic states, per-claim confidence and typed provenance, a provenance-gated expression rule, and a persistent revision store with auditable acknowledgments and partial resistance to false corrections. We evaluate it on a constructed, mechanically scored multi-session benchmark using a synthetic model and Qwen2.5-0.5B-Instruct. The synthetic instrument passes all five checks. On the real model, acknowledgment soundness, a by-construction guarantee, holds in 100% of cases, and true corrections are accepted more often than false ones (0.44 vs. 0.15 on held beliefs; 0.875 vs. 0.420 including rule-accepted corrections of unheld facts), but the pre-specified expression-fidelity, contradiction-separation, and provenance margins fail. A disclosed post hoc analysis shows that expression gated on mean answer-token probability ranks correctness below chance end to end (AUC 0.41, conversation-clustered), whereas gating on sampling consistency discriminates (AUC 0.66). A consistency-gated configuration selected from this finding and evaluated under a separately committed protocol meets the conversation-level manipulation and capability-equivalence criteria and replicates on a redrawn conversation set. The manipulation result is selection-dependent, and both criteria remain unresolved when uncertainty is clustered over the 60 facts. The supported conclusions are limited to the by-construction audit guarantee, store-dependent partial correction discrimination, and a benchmark- and model-specific failure of token-probability gating; scaling the fact base is required before human evaluation.
| Comments: | 17 pages, 4 figures, 3 tables. Companion framework paper: arXiv:2607.15883. Code, benchmark, cached model outputs, and result files archived at doi:https://doi.org/10.5281/zenodo.21462986 (code and results) and doi:https://doi.org/10.5281/zenodo.21462988 (benchmark dataset) |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.26035 [cs.CL] |
| (or arXiv:2609.26035v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.26035 arXiv-issued DOI via DataCite |
Submission history
From: Sebastian Cochinescu PhD (ABD) [view email]
[v1]
Tue, 22 Sep 2026 11:34:53 UTC (232 KB)
来源：arXiv cs.AI · arxiv.org