๐ Excited to share that our paper "APR: Adaptive Personalised Reranking For Conversational Search" (with @iadh and @debforit) has been accepted to @SIGIRConf 2026!
This will be my first SIGIR. See you in Melbourne!
#IR#ConversationalSearch#NLP#SIGIR2026
We ask the question: Can we address personalised user information needs in conversational search while still accommodating general queries? In this study, we investigate the use of instruction-following rerankers (like FollowIR) alongside similarity-based rerankers (like monoT5).
๐ PyTerrier Advent 10/25: Dense retrieval often improves with pseudo-relevance feedback (Rocchio-style).
In PyTerrier_DR itโs easy: retrieve docs, a transformer to mix doc vectors w/ the query vector, and re-retrieve.
https://t.co/NxQJYUcTIf
๐We want to try something new and fun this year โ an โAdvent Calendarโ of PyTerrier pipelines
Weโll kick it off with *the* baseline: BM25 on MSMARCO. One line to download a pre-built index, one line to make a BM25 retriever, one line to search.
We are happy to sponsor the Keith Van Rijsbergen (KvR) Award at #ECIR2026
๐ข ๐ก๐ผ๐บ๐ถ๐ป๐ฎ๐๐ถ๐ผ๐ป๐ ๐ฎ๐ฟ๐ฒ ๐ป๐ผ๐ ๐ผ๐ฝ๐ฒ๐ป!
Details and Submission Form: https://t.co/ciCJkp5X1U
๐ ๐๐ฒ๐ฎ๐ฑ๐น๐ถ๐ป๐ฒ: ๐ญ๐ฑ ๐๐ฎ๐ป๐๐ฎ๐ฟ๐ ๐ฎ๐ฌ๐ฎ๐ฒ
https://t.co/J1g36MWsD4
Weโre hiring a 2nd RA/PDRA at @GlasgowCS for the EU CLIMINVEST Project! Work with @iadh, @craig_macdonald & @richardm_ on LLM-powered AI agents for ESG & risk assessment in green investment. Apply by Dec 15: https://t.co/gBXIYo8je6
We are excited to announce that we are looking for PhD students for two projects funded by the EPSRC Doctoral Landscape Award!
Both projects explore how we can make LLMs more reliable and trustworthy with respect to writing better code or supporting safe clinical decisions.
๐งต
Overview of Self-Evolving Agents
There is a huge interest in moving from hand-crafted agentic systems to lifelong, adaptive agentic ecosystems.
What's the progress, and where are things headed?
Let's find out:
RA job in @ir_glasgow on an EU Horizon project, with @iadh@richardm_ and myself, on the use of LLMs in developing AI agents for the risk and ESG (Environmental, Social and Governance) assessment of sustainability-focused green investment projects. ๐
Self-Evolving AI Agents are about to blow up ๐๐ฅ
New Survey Alert ๐จ
From static LLMs โก๏ธ lifelong, adaptive agents ๐ฑ๐ค
A Comprehensive Survey of Self-Evolving AI Agents... โ your roadmap to the future of AI that learns & evolves after deployment! ๐ก
https://t.co/TBYfLLdaD1
๐ข Kicking off the day at the BioNLP Workshop with the opening talk!
๐งฌ Accelerating Cross-Encoders in Biomedical Entity Linking
With: @JavierSanzCruza & @jakelever0
๐ Room 2.15
๐ 08:50โ09:10
Drop by if youโre around โ would love to chat!
#BioNLP#ACL2025NLP#EntityLinking
We are seeking researchers interested in the topic proactive conversational information seeking grounded on the development of large language models. Join us, share your thoughts and findings! We are looking forward to hearing from you. #ProCISLLM@cikm2025
Heading to #ACL2025 this weekend โ Vienna, here we come! ๐ฆ๐น
Excited to share that the AI4BioMed Lab (led by @mengzaiqiao & @jakelever0) has three papers accepted this year! ๐
Come chat with us at the conference ๐
w/ @JinyuanF, @_xizhang, and @JavierSanzCruza ๐ฌ
๐ฎ Also, I'll be serving as Volunteer Coordinator on July 28 โ check your inbox if you're on shift!
@ir_glasgow@GlasgowCS@UofGlasgow
#NLP #AI4Health #RAG #MLLMs #BiomedicalNLP
The welcome reception at #ICDCS2025 is buzzing with energy! Fantastic to see so many smiling faces and lively conversations โ a vibrant start to the conference. Here's to a great main conference ahead! ๐
Want your LLMs to be safe and responsibly aligned? Time to vaccinate them! ๐งฌ
Fascinating #ICDCS2025 keynote by Ling Liu (Georgia Tech) on reducing fine-tuning costs while boosting safety in LLM deployment.