跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1020新增论文
+819其中 AI 相关
+116已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 14:52各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 15:36 — 2026-11-20 15:36(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 14:52库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

28,429 已收录论文23,606 AI 相关8,718 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
版本更新 · v2arXiv:2609.30780

Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI

Benedetta Picano, Dusit Niyato

原文摘要

Anthropomorphic conversational systems can provide companionship and emotional support, but repeated, seemingly harmless interactions can encourage excessive dependence and reduced human contact. We formulate safety in user-AI relationships as a sequential decision problem, using conversational cues to track the relationship and selecting responses according to their anticipated effects over time. A conditional Generative Flow Network learns from sampled response plans to select replies that preserve the largest estimated mass of safe and useful continuations. Model-based checks screen plans during training and responses during interaction, requiring at least one sequence of future response strategies that meets a prescribed safety bound under every candidate user model, independently of the learned network. Strategies are selected directly from learned first-step probabilities, avoiding online plan sampling. We evaluate the approach in simulation against reactive safeguards, filters with and without memory, and alternative planners, using exact computation to validate the learned approximation. We also evaluate relational cue extraction from real user messages in WildChat. To our knowledge, this is the first approach to select conversational replies by anticipating their effects on the user-AI relationship while imposing an explicit model-based safety bound on future response sequences. Results show close agreement with exact planning, lower decision costs at longer horizons, and improved safety-utility trade-offs when protective responses are less effective. The approach balances immediate support with the longer-term effects of repeated interaction. The source code is available at https://github.com/benedettapicano/ANTHROPOMORPHIC_SAFETY_TRAJ.

cs.HC