Check out the slides from our SCAI'2025 #convsearch workshop collocated with @ijcai.org #IJCAI2025 on LLMs, retrieval & QA, recommendations, negotiations, evaluation and transparency

scai.info/scai-2025

@patuchen.bsky.social @maik-froebe.bsky.social @tuetschek.bsky.social @mila-quebec.bsky.social

Or join us to hear about our own R&D work at the Workshop on Conversational Search for Complex Information Needs. convsearch-complex-info-needs.github.io #ecir2026

Join my research group @wuvienna.bsky.social working at the cutting edge of #IR and #ML!

1. Project Staff Member (3.5 years)
jobs.wu.ac.at/Project-staf...

2. Teaching & Research Associate (6 years)
jobs.wu.ac.at/Teaching-and...

#AI #PhDJobs #NeuroSymbolicAI #convsearch

I am hiring for 2 PhD positions on Information Retrieval & LLMs
@wuvienna.bsky.social

Apply until December 17th
wirtschaftsuniversitaet-wien-portal.rexx-systems.com/Project-staf...

#NLProc #RAG #IR #GenAI #convsearch

Changtai Zhu, Siyin Wang, Ruijun Feng, Kai Song, Xipeng Qiu
ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning
https://arxiv.org/abs/2505.15776

ConvSearch-R1 significantly outperforms previous state-of-the-art methods, achieving over 10% improvement on the challenging TopiOCQA dataset while using smaller 3B parameter models without any external supervision. [6/6 of https://arxiv.org/abs/2505.15776v1]

large language models, and insufficient alignment between the rewriting model and downstream retrievers. We present ConvSearch-R1, the first self-driven framework that completely eliminates dependency on external rewrite supervision by leveraging [3/6 of https://arxiv.org/abs/2505.15776v1]

Changtai Zhu, Siyin Wang, Ruijun Feng, Kai Song, Xipeng Qiu: ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement Learning https://arxiv.org/abs/2505.15776 https://arxiv.org/pdf/2505.15776 https://arxiv.org/html/2505.15776