Papers by Qitan Lv
Exploiting Edited Large Language Models as General Scientific Optimizers (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for solving optimization problems in scientific scenarios use observational feedback as additional textual descriptions, but these methods struggle to utilize it effectively. |
| Approach: | They propose a generalized approach to boost mathematical optimization in scientific scenarios by using observational feedback from LLMs as additional textual descriptions. |
| Outcome: | The proposed method outperforms existing state-of-the-art methods on six different tasks using six different LLM backbones. |
SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graph (2024.acl-long)
Copied to clipboard
| Challenge: | Existing KG construction methods rely on human intervention to attain qualified KGs, which severely hinders the practical application of domain KG. |
| Approach: | They propose a general KG construction framework that uses large language models as "S**killed" A**utomatic C**onstructors for domain knowledge (G**raph) |
| Outcome: | The proposed framework generates specialized multi-level knowledge graphs at the scale of over one million nodes and achieves 89.32% precision rate compared to state-of-the-art methods. |
LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation (2026.findings-acl)
Copied to clipboard
| Challenge: | Speculative decoding (SD) is a promising technique for LLM inference acceleration. |
| Approach: | They propose a method to generate draft tokens in a retrieval-based manner to reduce drafting overhead and improve inference speed. |
| Outcome: | Extensive tests show that *LogitSpec* can achieve 2.61 speedup and 3.28 mean accepted tokens per decoding step. |