We're very excited to be starting an #NLProc lab at Duke in Fall 2021, and we're looking for PhD students! We'd especially like to encourage applicants from nontraditional backgrounds and communities historically underrepresented in the field. Apply here:

RT @bhuwandhingra: Citations are crucial for improving the trustworthiness of LLM outputs. But can we train LLMs to cite their pretraining….

RT @RoyXie_: Can we train reasoning LLMs to generate answers as they think?.Introducing 𝐈𝐧𝐭𝐞𝐫𝐥𝐞𝐚𝐯𝐞𝐝 𝐑𝐞𝐚𝐬𝐨𝐧𝐢𝐧𝐠! We train LLMs to alternate….

RT @bhuwandhingra: Glad to share a new ACL Findings paper from @MaxHolsman and @YukunHuang9!. We introduce Fuzzy Speculative Decoding (FSD)….

RT @bhuwandhingra: 📢 New Preprint from @raghavlite on Multimodal Contrastive Learning: Breaking the Batch Barrier (B3) 📢. TL;DR: Smart batc….

RT @JunlinWang3: Excited to share work from my @togethercompute internship—a deep dive into inference‑time scaling methods 🧠. We rigorously….

RT @bhuwandhingra: At #ICLR2025? Check out @YukunHuang9 ‘s poster tomorrow on when to trust external contexts using LLMs. .

RT @bhuwandhingra: **New paper from @RoyXie_ **. Do LLMs know when they have read enough to answer a question?. We show how language models….

RT @ghazalkhn: 📢 New preprint on a benchmark for multimodal information extraction! . Structured data extraction from long documents consis….

RT @bhuwandhingra: 🧵When should LLMs trust external contexts in RAG?. New paper from @YukunHuang9 and @sanxing_chen enhances LLMs’ *situat….

RT @ghazalkhn: 🎉 Excited to share that IsoBench has been accepted at @COLM_conf!. IsoBench features isomorphic inputs across Math/Graph pro….

RT @ruoyuxyz: 🚨 Breaking: >90% AUC on the WikiMIA dataset for membership inference!. Want to know if your data is in LLM's training set?🔍….

RT @JunlinWang3: 🦝Excited to announce our work on robustness & security of LLM systems! 𝐑𝐚𝐜𝐜𝐨𝐨𝐧: Prompt Extraction Benchmark of LLM-Integra….

Welcome to Duke!.

RT @bhuwandhingra: 🧐 Can we generate *LLM-proof* math problems❓. 👉Check out the new preprint from @ruoyuxyz , Chengxuan Huang and @JunlinWa….

RT @Jinho_D_Choi: 150+ people registered for the SouthNLP 2024 at Emory University on 4/5. The schedule is available on our website: https:….

RT @bhuwandhingra: New Preprint from @YukunHuang9!. Can an LLM determine when its responses are incorrect? Our latest paper dives into "Cal….

RT @phyllis_ang_: Increasing the input length often increases accuracy on NLP tasks like summarization. But given limited time and a fixed….

RT @bhuwandhingra: 🤔 When does a factoid question need a *long* answer?.🤖 "Long" could mean multiple things: either you ask for a city with….

RT @mohitban47: See a glimpse👇of how beautiful @unc +research triangle fall colors are 😍. Come join our awesome group of @uncnlp @unccs stu….

The DukeNLP group is hiring PhD students in all areas of natural language processing! Apply at by Dec 15 to work with @_samwiseman or @bhuwandhingra.