Hang Li

Postdoc & Former PhD @IELabGroup UQ 🇦🇺. BSc. @UMNComputerSci 🇺🇸 alumni. Information Retrieval, LLM.

[Hang Li @hanglics]

@dylan_wangs @joelmmackenzie You even spelled Dr. Mackenzie’s name wrong 🤪

[Hang Li @hanglics]

@dylan_wangs @joelmmackenzie No you are not

[Hang Li @hanglics]

@joelmmackenzie Can I do another PhD with you, my boss? 😆

[Joel Mackenzie @joelmmackenzie]

I'm looking for a #PhD student who is interested in scalable #algorithms and data structures. Please share on if you know anyone who may be interested! https://t.co/XyRd2VEU6M

#rust #systems #algorithms #search #bioinformatics #UQ #Brisbane #toomanyhashtags

[Hang Li @hanglics]

I'm claiming my AI agent "jarvisuq" on @moltbook 🦞

Verification: antenna-C54U

[Alex Cui @alexcdot]

Okay so, we just found that over 50 papers published at @Neurips 2025 have AI hallucinations

I don't think people realize how bad the slop is right now

It's not just that researchers from @GoogleDeepMind, @Meta, @MIT, @Cambridge_Uni are using AI - they allowed LLMs to generate hallucinations in their papers and didn't notice at all.

It's insane that these made it through peer review👇

[Glasgow IR Group @ir_glasgow]

🎄 PyTerrier Advent 10/25: Dense retrieval often improves with pseudo-relevance feedback (Rocchio-style).

In PyTerrier_DR it’s easy: retrieve docs, a transformer to mix doc vectors w/ the query vector, and re-retrieve.
https://t.co/NxQJYUcTIf

[Craig Macdonald @craig_macdonald]

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. 👇

[ielab @IELabGroup]

🎉 Excited to share the list of our @IELabGroup papers accepted at #SIGIR2025 @ACMSIGIR! Topics include efficiency in IR, domain-specific IR (SysRev, podcast), screenshot retrievers, hallucination detection, and more. See you in Padua 🇮🇹!
Details coming soon, stay tuned!

[Sumit @_reachsumit]

I published Vol. 96 of "Top Information Retrieval Papers of the Week" on Substack.
🔗 https://t.co/dGCa1ZiCx6

[Sumit @_reachsumit]

Pseudo-Relevance Feedback Can Improve Zero-Shot LLM-Based Dense Retrieval

@hanglics et al. show how LLMs can extract features from top-ranked documents, enabling smaller rankers with PRF to match larger rankers without PRF.

📝https://t.co/nzm9p1BYS2

[Sumit @_reachsumit]

Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning

@ShengyaoZhuang et al. introduce a LLM-based reranker that performs reasoning over queries and candidate documents before ranking.

📝https://t.co/ptj5wHqfip

[Shengyao Zhuang @ShengyaoZhuang]

We introduce Rank-R1, an LLM-based document reranker featured with reasoning abilities. Joint work with @xueguang_ma @bevan_koopman @lintool @guidozuc
Check out the paper: https://t.co/vCWqFJ5xt0
and we open-sourced model checkpoints and our code at:
https://t.co/V1KuXrpQga

[Aixin Sun @AixinSG]

Our understanding of knowledge updating: Do not modify model parameters. https://t.co/SzgZICRpcF

[homanp @pelaseyed]

RIP ”Needle in the haystack” 🪦

For all my RAG/vectorstore fanboys out there who keep betting against the models.

[Perplexity @perplexity_ai]

A message from our new Chief Security Officer at Perplexity:

[SIGIR 2025 @SIGIRConf]

📣 📣 The #sigir2025 LiveRAG Challenge is open at:

https://t.co/1lgSaMoXTk

Prizes:
- First Prize: $5000
- Second Prize: $3000
- Third Prize: $2000

Deadlines:
- Application submission deadline: February 24, 2025

More info? Ask [email protected].

[will brown @willccbb]

deepseek is passing the chatgpt detector tests with flying colors

[Tanishq Mathew Abraham, Ph.D. @iScienceLuvr]

Anyone who thinks DeepSeek just came out of nowhere should see this graph.

For each model on this graph, weights, code, and detailed papers were released.

This is a team with a strong track record and has been working hard for a while. They didn't come out of nowhere.

[Jimmy Lin @lintool]

Sharing this gem with the world, unearthed while cleaning out personal files: History of open-source IR systems, dating to 1985 with the release of SMART (yes, 40 years ago), and even further back! https://t.co/mu2i3RkZkG