TL;DR Advanced encoders were losing to older models on sparse retrieval for one surprising reason: a vocabulary mismatch. Fixing it with just 20k adaptation steps sets a new BEIR state of the art. Title: Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps URL: Key points 🔤 Raw case-sensitive vocabularies were splitting single meanings across redundant surface forms 🧩 The proposed Vocabulary Transfer method migrates vocabularies in 3 lightweight steps 📊 ModernBERT-VT hits nDCG@10 52.4 on BEIR, a new SOTA 💥 A collapsed RoBERTa-large jumps from BEIR score 1.4 to 51.3 ⚡ Uses under 0.2% of the original pretraining token budget 🧪 Near-optimal performance reached in just 500 MLM steps 🧬 Also works for domain-specific vocabularies like chemistry It's a nice reminder that what looked like an architectural ceiling turned out to be a fixable vocabulary design problem. #InformationRetrieval# #LLM#

3 ways I'm using Grok Bot plugins Information retrieval: First, you can ask questions and pull context from multiple workspaces, slacks, and google accounts - Grok @Bot supports multiple accounts per connection. This is helpful when information is scattered or you find yourself switching between multiple apps. Grok Bot has saved me hours as a simple search tool. "I think I saw an invite for an event on Friday, but I can't remember if it was in Slack or Gmail - can you find it for me?" Bi-directional sync: Because Grok Bot has triggers & routines - you can make a zero-code bi-directional sync: "Make sure events on my personal calendar are always blocked on my work calendar" Or get more advanced: "Every Monday, take my tasks in Todoist and Google Calendar and block time on my work calendar for deep work, hold time for personal events (going to the gym, etc), and ensure each task has some time scheduled" Sync across channels: I use Grok Bot to make sure I capture feedback across channels and sync deliverables. Because Grok Bot can kick off cloud agents, this is perfect for flows with tons of context switching. "There's a launch happening this Friday, I have a draft for the changelog on GitHub, but the team is leaving feedback in Notion and Slack. The header asset is in Figma. Keep an eye on the feedback and consolidate it for me here. Then, kick off a Cursor cloud agent to update the PR and make adjustments in Figma as necessary" This has drastically reduced context switching typically associated with knowledge work and allowed me to focus more on what matters - being creative. I found plugins to be one of the biggest differentiators from other personal agents. Shout out to the team for the rock-solid experience.

Financial work depends on trustworthy sources, consistent definitions, accurate calculations and auditable outputs. Introducing Ling-3.0-flash-Fin, a finance-enhanced version of Ling-3.0-flash, developed with financial institutions and domain experts. With 124B total and 5.1B active parameters, it supports information retrieval, research, valuation modeling and report preparation across long reports, research materials and complex workbooks. The model showed competitive results across FinFIRST, FinSearchComp Verified, FinCRAFT, FinanceAgent v1.1/v2, APEX-Agents, SpreadsheetBench v1/v2 and τ³-Banking. We will open-source the model weights next week.