Jing Xiong
@_June1126
Phd student in HKU. Research Direction: Efficient Natural Language Processing and Automated Theorem Proving
🌟Excited to share LeCo's acceptance at #COLM2024! 🤔Fed up with LLMs' self-correct struggles and endless prompts? 🪄LeCo uses logits for confidence scores, skipping tedious prompts and rethinking from the last correct step. 📖:arxiv.org/abs/2403.19094 💻:github.com/starrYYxuan/Le…
Excited to announce our paper's acceptance at ICLR 2024! 🌟 Our algorithm leverages CoT for enhanced in-context exemplar selection, optimizing it with a unique mapping function. Dive in: 📄[Paper](arxiv.org/abs/2310.02954) 💻[Code](github.com/AI4fun/DQ-LoRe) #ICLR2024 #AI #NLP #LLMs
UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation Uses SNR-based span uncertainty for improved chunk similarity estimation, offering flexible integration across various LLMs without fine-tuning. 📝arxiv.org/abs/2410.02719
📷 New Benchmark Release: PhyX - Physical Reasoning for Multimodal Models 👉 Project Page: phyx-bench.github.io 👉 Github: github.com/NastyMarcus/Ph… 👉 arXiv: arxiv.org/abs/2505.15929 👉 Huggingface Dataset: huggingface.co/datasets/Cloud…
🔥Thrilled to announce our Oral acceptance at #NeurIPS2024! 🚀HydraLoRA, an asymmetric LoRA architecture with a shared A matrix for common knowledge and multiple B matrices for specialized adaptations, enhancing model performance while maximizing efficiency with a reduced param.
+👋LLMs work quite well on modeling/understanding long context. What about generating long content 🤔 Check our ACL paper ProxyQA for evaluating Long-Form Generation (way longer🪘🪘 📝Paper: arxiv.org/abs/2401.15042 🐙Code: github.com/Namco0816/Prox…
Excited to reveal our ACL 2024 Paper! 🎉 Struggling with evaluating LLM’s long-form content generation? Find string-matching metrics outdated? Manual evaluation too taxing? Doubtful of LLM-as-judge results? Give ProxyQA a shot! 🎯 📝Paper: arxiv.org/abs/2401.15042
🔥New paper!📜 Struggle to align LLM evaluators with human judgements?🤔 Introducing PairS🌟: By exploiting transitivity, we push the potential of pairwise preference in efficient ranking evaluations that has better alignment!🧑⚖️ 📖arxiv.org/abs/2403.16950 💻github.com/cambridgeltl/p…
翻到一篇文章[ICLR'24]Understanding Addition in Transformers 回忆起在初学oi年代被老师问了一道题：怎么直接按从左到右的顺序直接做大整数加法，不允许读完再翻转。当时想了十分钟想到一个存9和进位链的做法，被老师夸了。但我觉得这题没现实意义 没想到LLM因为必须从左到右写，也悟出了一样的算法