---
title: "Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.38755v1"
permalink: "https://feed.astralor.com/items/itm_2fd9214809635d319f547b92"
published: "2026-10-28T19:35:59.000Z"
score: 52
channel: "tech"
tags: ["LLM","推理效率","多模态","Leaving","Staying","Living There","Duration Commonsense Reasoning","Human-LLM Co-annotations Gardening"]
---

# Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations

## 速览

Gardening in the backyard implies living there, while checking into an Airbnb more likely means staying for a few days. Such duration judgments are important for understanding human mobility, travel behavior, and social…

## 关键点

- Gardening in the backyard implies living there, while checking into an Airbnb more likely means staying for a few days.
- Such duration judgments are important for understanding human mobility, travel behavior, and social context.
- However, duration is rarely stated explicitly in social media posts and must instead be inferred from noisy textual, visual, and contextual cues.

## 全文

Gardening in the backyard implies living there, while checking into an Airbnb more likely means staying for a few days. Such duration judgments are important for understanding human mobility, travel behavior, and social context. However, duration is rarely stated explicitly in social media posts and must instead be inferred from noisy textual, visual, and contextual cues. In this paper, we investigate whether vision-language models possess such duration commonsense. We create a new corpus of geotagged tweets co-annotated by humans and LLMs to serve as a testbed for this task. We find that state-of-the-art models struggle with duration inference, even when guided by multi-turn Chain-of-Thought prompting. Error analyses further reveal that models often fail to integrate critical contextual information, or they overly rely on prominent visual details while overlooking subtle hashtags and semantic nuances. These findings underscore the significant challenges remaining in context-aware multimodal understanding.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_2fd9214809635d319f547b92