结构感知+证据引导，让知识型视觉问答的推理过程更可信、可验证。
arXiv:2608.21796v1 Announce Type: cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning…
发现单个神经元就能像旋钮一样控制LLM的投资偏见，精准干预AI决策倾向。
arXiv:2608.22852v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in investment decision-making, yet prior work shows…
LLM为何爱说漂亮话？这项研究让模型“开口”解释自己的假设，并教你精准控制谄媚行为。
arXiv:2604.03058v3 Announce Type: replace-cross Abstract: LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the …
用强化学习让大模型学会「讲道理」，逆合成预测从黑箱猜测走向可解释推理——AI驱动分子设计又进一步。
arXiv:2507.17448v2 Announce Type: replace-cross Abstract: Retrosynthetic planning is a cornerstone of organic synthesis and drug discovery. Yet existi…
用Token相关性拆解大模型为何会答应不道德请求，为AI安全审计提供新视角。
arXiv:2608.23264v1 Announce Type: new Abstract: Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, t…
机械可解释性揭示大模型内在道德自我修正的机制，为AI安全对齐提供新视角。
arXiv:2505.11924v4 Announce Type: replace-cross Abstract: Intrinsic moral self-correction refers to the phenomenon where a language model refines its …
IT之家 8 月 22 日消息，GPD Win Max 3 掌机最初亮相于今年 6 月，搭载 AMD Strix Halo 平台，拥有 165Hz AMOLED 屏幕和可光环电池。如今该公司已公布 Win Max 3 的众筹上线日期，同时也揭晓了该机的定价。 据悉，Win Max 3 上市时将提供三…
一步错步步错？实测三类信用信号在LLM智能体训练中均无法锁定关键步骤，揭示因果归因盲区。
arXiv:2608.19760v1 Announce Type: new Abstract: Audited against causal ground truth from executed replay in a single-agent tool environment (ALFWorld)…
揭秘LLM裁判在推荐解释中的全生命周期，从训练到部署的工程实践与挑战一网打尽。
arXiv:2608.18300v1 Announce Type: new Abstract: LLM-as-a-Judge, which leverages a large language model to evaluate natural language generated by anoth…
用通用多模态大模型把深度伪造检测变成可解释的感知工具，让AI“说”出造假痕迹。
arXiv:2608.18573v1 Announce Type: new Abstract: Existing explainable deepfake forensic methods typically rely on task-adapted MLLM to jointly address …
大模型的思维链并非真实决策的审计日志，揭开推理可解释性的关键盲区。
Article URL: https://rye.ai/blog/cot-faithfulness-reasoning-traces-not-audit-logs/ Comments URL: https://news.ycombinator.com/item?id=49371034 Points:…
用追溯图把智能体回答与证据链绑定，审计大模型不再黑箱。
arXiv:2608.18398v1 Announce Type: cross Abstract: Large language model (LLM) agents can now carry out long-horizon technical workflows involving compl…
把推理规则内化进语言模型，让知识图谱推理更忠实可靠，值得关注的前沿方法。
arXiv:2608.17443v1 Announce Type: new Abstract: Knowledge Graph Reasoning (KGR) aims to discover latent facts by leveraging the structural evidence av…
混合专家模型内部藏着幻觉检测信号，为可信AI提供新思路。
arXiv:2608.17687v1 Announce Type: new Abstract: Despite their widespread use, Large Language Models (LLMs) remain limited by a fundamental problem: th…
时间问答遇上可解释推理：用语义时间自动机拆解复杂时序问题，让模型推理过程透明可控。
arXiv:2608.16224v1 Announce Type: cross Abstract: By leveraging large-scale pretraining, LLMs can interpret diverse temporal expressions and question …
深度学习中模型学到的是真实生物信号还是伪影？ICML 2026 论文以生物成像为例，拷问表征学习的本质，值得每一位科研工作者反思。
arXiv:2603.13377v2 Announce Type: replace-cross Abstract: Representation learning has driven major advances in natural image analysis by enabling mode…
揭秘大模型幻觉根源：MoRFI方法用单调稀疏自编码器精准锁定知识特征，为可解释性带来新突破。
arXiv:2604.26866v2 Announce Type: replace-cross Abstract: Large language models (LLMs) acquire most of their factual knowledge during the pre-training…
把Kimi K3的权重渲染成3D城市：24.9万个张量、896个专家一目了然，AI内部结构从未如此直观。
Article URL: https://magik.net/llmcity/ Comments URL: https://news.ycombinator.com/item?id=49333151 Points: 2 # Comments: 1
一篇论文揭示如何追踪LLM推理环节与偏见输出的因果链条，给AI可解释性提供新工具
arXiv:2608.14161v1 Announce Type: new Abstract: LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in …