提出概率置信度选择与排序方法，优化大模型推理链，提升复杂推理的准确性与可解释性。
arXiv:2508.21787v3 Announce Type: replace-cross Abstract: Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning…
物理运动感知与置信度引导LLM结合的生成推理新方法，被ECCV 2026接收
arXiv:2505.16456v3 Announce Type: replace Abstract: Recent advances in 3D content generation have amplified demand for dynamic models that are both vi…
系统解剖LLM中不确定性的来源与量化方法，为可信AI提供理论基础。
arXiv:2603.24967v2 Announce Type: replace Abstract: Understanding why a large language model (LLM) is uncertain about the response is important for th…
开源项目Aletheia探索无测试集下的循环工程，通过明确不确定性视图和矛盾证据降低置信度，为Claude Code和Codex注入推理智能。
Aletheia is an open-source attempt to explore what loop engineering looks like when reality has no test suite. It maintains an explicit view of what m…
最新论文提出Fork-Think方法，通过分叉思考增强置信度，提升推理可靠性。
arXiv:2606.31484v1 Announce Type: new Abstract: Parallel thinking has enjoyed great success for boosting LLM performance on reasoning tasks without th…
LLM说“我很有把握”其实更代表“我坚持选它”，而非正确答案——揭秘AI置信度的真实含义。
arXiv:2606.29490v1 Announce Type: new Abstract: Confidence is an estimate of the probability that a chosen answer is correct. Verbal confidence report…
研究修剪注意力层如何影响LLM的解释忠实性与置信度校准，揭示模型优化新视角。
arXiv:2606.24970v1 Announce Type: new Abstract: Pruning Large Language Models (LLMs) reduces memory and inference costs by removing parts of the netwo…
基于置信度和提示注入检测，为OpenAI智能体行动加一道安全门，60秒本地部署。
Article URL: https://github.com/Lelu-ai/lelu Comments URL: https://news.ycombinator.com/item?id=48664025 Points: 4 # Comments: 0
大语言模型看似自信输出时，内部却在处理认知失调，这篇论文揭示了这种矛盾心理机制。
arXiv:2606.22633v1 Announce Type: new Abstract: Large language models (LLMs) frequently encounter inputs that disagree with their prior outputs, throu…
揭示AI agent系统中“置信度洗钱”现象，论证不确定性为何需要潜在载体的前沿理论。
arXiv:2606.20662v1 Announce Type: new Abstract: Modern agent systems can turn uncertainty into overconfidence. Fragile upstream decisions are often ex…
AI定位bug根源是真实诊断还是自信胡诌？本文揭示LLM听起来合理但未必正确的陷阱。
We built Pinaka to write root cause analyses automatically — read a Jira ticket, search the codebase, trace the failure, post the RCA as a comment. Be…
新方法量化LLM在上下文学习中的偶然不确定性，提升预测置信度的鲁棒性，已被ACL 2026接收。
arXiv:2606.19353v1 Announce Type: cross Abstract: In-Context Learning (ICL) allows LLMs to adapt to new tasks from a few demonstrations, but its relia…
用Tsetlin机器实现目标置信度的反事实追索，为模型可解释性提供新思路
arXiv:2606.18832v1 Announce Type: new Abstract: Counterfactual explanations are widely used to provide algorithmic recourse in high-stakes decision-ma…
大模型CoT推理中置信度与理由对齐的新方法，GRPO优化让推理更可靠。
arXiv:2606.14961v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning can improve LLM performance, but high answer confidence may be mislea…
LLM置信度评分尺度（0-100）并非中性设计，新研究揭示其对元认知表现的显著影响。
arXiv:2603.09309v2 Announce Type: replace Abstract: Verbalized confidence, in which LLMs report a numerical certainty score, is widely used to estimat…
利用不同模型间的分歧作为无标签正确性信号，破解自信错误检测难题。
arXiv:2603.25450v2 Announce Type: replace Abstract: Detecting when a language model is wrong without ground truth labels is a fundamental challenge fo…
基于早期token置信度，预测多智能体LLM辩论的推理质量，为高效协调提供新思路。
arXiv:2606.10307v1 Announce Type: new Abstract: Evaluating reasoning quality in multi-agent LLM systems is challenging, especially for open-ended task…
颠覆传统：让LLM先评估自身置信度再作答，大幅提升不确定性估计效率
arXiv:2603.05881v2 Announce Type: replace Abstract: Reliable deployment of large language models (LLMs) requires accurate uncertainty estimation. Exis…
提出评估和校准LLM在有多正确答案问题上的置信度方法，提升模型可靠性与可信度。
arXiv:2602.07842v2 Announce Type: replace Abstract: Confidence calibration is essential for making large language models (LLMs) reliable, yet existing…
探索大型推理模型如何忠实表达置信度，量化方法带来新视角
arXiv:2606.03969v1 Announce Type: cross Abstract: Reliable uncertainty communication is critical to the trustworthiness of LLMs, yet faithful calibrat…