paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
HS

Heydar Soudani

SIGIR 2026×2检索与知识推理评测与基准
新星分新星
69
一作贡献40
核心/参与12
方向广度6
合作网络6
1 一作 · 2 篇 · SIGIR 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

2
一作SIGIR 2026Oral· Information Retrieval (Full)

Uncertainty Quantification for Retrieval-Augmented Reasoning

Heydar Soudani · Hamed Zamani · Faegheh Hasibi

摘要

Retrieval-augmented reasoning (RAR) is a recent evolution of retrieval-augmented generation (RAG) that employs multiple reasoning steps for retrieval and generation. While effective for some complex queries, RAR remains vulnerable to errors and misleading outputs. Uncertainty quantification (UQ)...

检索与知识推理评测与基准OpenReview
作者位次 #2/6SIGIR 2026Poster· Information Retrieval (Resource)

Total Recall QA: A Verifiable Evaluation Suite for Deep Research Agents

Mahta Rafiee · Heydar Soudani · Zahra Abbasiantaeb · Mohammad Aliannejadi · Faegheh Hasibi · Hamed Zamani

摘要

Deep research agents have emerged as LLM-based systems designed to perform multi-step information seeking and reasoning over large, open-domain sources to answer complex questions by synthesizing information from multiple information sources. Given the complexity of the task and despite various r...

检索与知识评测与基准推理OpenReview

常见合作者