Jimmy Lin retweeted
The official version of our paper “Don’t ‘Overthink’ Pointwise Reranking: Is Reasoning Truly Necessary?” is out! 🎉
📄 aclanthology.org/2026.findings-…
See the 🧵 below for details! 👇
📄 aclanthology.org/2026.findings-…
See the 🧵 below for details! 👇
Excited to share that our paper was accepted to EMNLP Findings 🎉
We ask a simple question: Does reasoning improve pointwise rerankers?
The answer? It can actually hurt... even for Rank1, a reranker trained to reason-then-answer 😱
📄 nourj98.github.io/papers/dont-ov…
0
2
8
404
Jimmy Lin retweeted
Love BrowseComp-Plus? Meet 𝐂𝐌𝐀𝐒𝐒! 🚀
cmass.tech
🔥Your next challenge for agentic search: 423 question–answer pairs spanning BrowseComp-Plus, DeepSearchQA, Total Recall QA, and HotpotQA—all projected onto ClimbMix, a realistic corpus of over 550M documents.
cmass.tech
🔥Your next challenge for agentic search: 423 question–answer pairs spanning BrowseComp-Plus, DeepSearchQA, Total Recall QA, and HotpotQA—all projected onto ClimbMix, a realistic corpus of over 550M documents.
2
8
25
1,010
tl;dr - the team @Sahel_Sharify @Lingwei_Gu @nour_jedidi speedran nanochat by @karpathy using ClimbMix by @shizhediao et al. and then SFT'ed on relevance data from @beirmug @crystina_z to arrive at a competitive pointwise reranker: arxiv.org/abs/2610.11922
3
10
42
3,471
What are we up to? 🏡 Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search w/ @Sahel_Sharify @Lingwei_Gu @nour_jedidi arxiv.org/abs/2610.11922
1
19
43
3,518
You mean, building things that are actually useful... and that people care about? Nice but how unacademic! 👍 Congratulations! I look forward to learning more! ❤️
We are releasing the most significant technology transfer effort by the CIIR in the last decade. Please share with your network.
In this thread you will learn what Nage enables you to do.
🧵👇
0
1
13
1,766
Jimmy Lin retweeted
PhD defended today! 🎓
Huge thanks to my supervisor @WenhuChen for all the guidance and support throughout this journey, and to all my committee members for their time, thoughtful questions, and feedback.
Next stop: joining Meta FAIR as a Research Scientist. Excited for what’s ahead!
Huge thanks to my supervisor @WenhuChen for all the guidance and support throughout this journey, and to all my committee members for their time, thoughtful questions, and feedback.
Next stop: joining Meta FAIR as a Research Scientist. Excited for what’s ahead!
43
11
245
31,535
Jimmy Lin retweeted
Excited to share that our paper was accepted to EMNLP Findings 🎉
We ask a simple question: Does reasoning improve pointwise rerankers?
The answer? It can actually hurt... even for Rank1, a reranker trained to reason-then-answer 😱
📄 nourj98.github.io/papers/dont-ov…
We ask a simple question: Does reasoning improve pointwise rerankers?
The answer? It can actually hurt... even for Rank1, a reranker trained to reason-then-answer 😱
📄 nourj98.github.io/papers/dont-ov…
🚨Do passage rerankers really need explicit reasoning?🤔—Maybe Not!
Our findings:
⚖️Standard rerankers outperform those w/ step-by-step reasoning!
🚫Disable reasoning from reasoning reranker actually improves reranking accuracy!🤯
👇But, why?
📰arxiv.org/abs/2505.16886
(1/6)
2
8
26
2,448
Jimmy Lin retweeted
To make an LLM a strong dense retriever, you often need training…
But what if you only have a few-examples 🥩🥦 and no training budget?
Just add RICE 🍚, a simple way to turn your LLM into an effective dense retriever that requires zero training 👨🍳
📄 arxiv.org/abs/2609.38099
But what if you only have a few-examples 🥩🥦 and no training budget?
Just add RICE 🍚, a simple way to turn your LLM into an effective dense retriever that requires zero training 👨🍳
📄 arxiv.org/abs/2609.38099
3
7
31
2,287
Yo, I heard you like leaderboards. So I created another one: with ACM Fellows and Turing Award winners. Another target for citation and h-index benchmaxxing. 💪 lintool.github.io/acm-bigcows/ac…
1
0
13
4,582
Summer passed in a blur... 🏖️🦩🍹 and I forgot to congratulate @HosnaOH for finishing her Master's! Her work with @amirhkarimi_ "A Unified Perturbation Framework for Analyzing Leaderboard Stability and Manipulation" arxiv.org/abs/2605.15761 just got a +1 from NeurIPS, so yay! 🎉
1
2
51
3,840
Achievement unlocked! 🔓 Does this come with stat bonuses or help with saving throws? uwaterloo.ca/computer-scien…
36
9
147
6,700
My colleague @yuntiandeng about “Claudish” 🤖 and how AI coding agents are changing the way we communicate! uwaterloo.ca/news/media/q-a…
1
1
10
2,755
Jimmy Lin retweeted
1/ 🧵
BrowseComp-Plus (ACL 2026) set the standard for disentangled agentic search eval...
🙌 𝐁𝐫𝐨𝐰𝐬𝐞𝐂𝐨𝐦𝐩-𝐏𝐥𝐮𝐬_𝐂𝐌 makes it even better!
🚀 Same BCP questions grounded on 𝐂𝐥𝐢𝐦𝐛𝐌𝐢𝐱-𝟒𝟎𝟎𝐁 with 𝟓𝟓𝟑𝐌 𝐝𝐨𝐜𝐬.
💻 github.com/castorini/cmass
BrowseComp-Plus (ACL 2026) set the standard for disentangled agentic search eval...
🙌 𝐁𝐫𝐨𝐰𝐬𝐞𝐂𝐨𝐦𝐩-𝐏𝐥𝐮𝐬_𝐂𝐌 makes it even better!
🚀 Same BCP questions grounded on 𝐂𝐥𝐢𝐦𝐛𝐌𝐢𝐱-𝟒𝟎𝟎𝐁 with 𝟓𝟓𝟑𝐌 𝐝𝐨𝐜𝐬.
💻 github.com/castorini/cmass
🚀 Introducing BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent.
It is a new Deep-Research evaluation benchmark built on top of BrowseComp. It features
- 📚 a fixed, carefully curated corpus of web documents
- ✅ human-verified positive d challenging hard negatives.
With BrowseComp-Plus, you can thoroughly evaluate and compare the performance of different components in a deep-research system. e.g. GPT-5 + Qwen3-Embedding.
Code, dataset, and leaderboard links are provided at the end of this thread.
1
9
34
4,555
Jimmy Lin retweeted
In the past year, we've seen rapid progress in search agents! However, how well do these search agents work outside English?
Introducing⛵️MAST @🔥FIRE 2026, a new shared task focused on multilingual agentic search.
Introducing⛵️MAST @🔥FIRE 2026, a new shared task focused on multilingual agentic search.
1
8
31
6,380
