diff --git a/data/xml/2022.coling.xml b/data/xml/2022.coling.xml index fe0033be1e..f738f5e057 100644 --- a/data/xml/2022.coling.xml +++ b/data/xml/2022.coling.xml @@ -5168,7 +5168,7 @@ On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation ChangtongZan LiangDing - LiShen + LiShen YuCao WeifengLiu DachengTao diff --git a/data/xml/2022.findings.xml b/data/xml/2022.findings.xml index c7c721e9e0..1e17d40ce1 100644 --- a/data/xml/2022.findings.xml +++ b/data/xml/2022.findings.xml @@ -12137,7 +12137,7 @@ Faster and Smaller Speech Translation without Quality Compromise Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models QihuangZhongWuhan University LiangDingJD Explore Academy, JD.com Inc. & The University of Sydney - LiShenJD Explore Academy + LiShenJD Explore Academy PengMiXiamen University JuhuaLiuWuhan University BoDuWuhan University diff --git a/data/xml/2023.emnlp.xml b/data/xml/2023.emnlp.xml index a30757ed6f..94ce15ec35 100644 --- a/data/xml/2023.emnlp.xml +++ b/data/xml/2023.emnlp.xml @@ -9715,7 +9715,7 @@ Zero-shot Sharpness-Aware Quantization for Pre-trained Language Models MiaoxiZhu QihuangZhong - LiShen + LiShen LiangDing JuhuaLiu BoDu @@ -12674,7 +12674,7 @@ The experiments were repeated and the tables and figures were updated. Changes a ShwaiHe Run-ZeFan LiangDing - LiShen + LiShen TianyiZhou DachengTao 14685-14691 diff --git a/data/xml/2023.findings.xml b/data/xml/2023.findings.xml index 80ad9ca38b..d0da8c7344 100644 --- a/data/xml/2023.findings.xml +++ b/data/xml/2023.findings.xml @@ -19530,7 +19530,7 @@ KeqinPeng LiangDing QihuangZhong - LiShen + LiShen XueboLiu MinZhang YuanxinOuyang diff --git a/data/xml/2024.acl.xml b/data/xml/2024.acl.xml index 0c24f4b3ba..87b1aa5b6f 100644 --- a/data/xml/2024.acl.xml +++ b/data/xml/2024.acl.xml @@ -8162,7 +8162,7 @@ Revisiting Knowledge Distillation for Autoregressive Language Models QihuangZhong LiangDing - LiShenSun Yat-Sen University + LiShenSun Yat-Sen University JuhuaLiuWuhan University BoDuWuhan University DachengTaoUniversity of Sydney diff --git a/data/xml/2024.emnlp.xml b/data/xml/2024.emnlp.xml index cb09c5b5cd..631e4f7338 100644 --- a/data/xml/2024.emnlp.xml +++ b/data/xml/2024.emnlp.xml @@ -13939,7 +13939,7 @@ Cheng-YuHsiehUniversity of Washington Ajay KumarJaiswalApple TianlongChen - LiShen + LiShen RanjayKrishnaDepartment of Computer Science ShiweiLiu 18089-18099 diff --git a/data/xml/2024.findings.xml b/data/xml/2024.findings.xml index cbffc13d45..8aeb5fd27e 100644 --- a/data/xml/2024.findings.xml +++ b/data/xml/2024.findings.xml @@ -17100,7 +17100,7 @@ <fixed-case>OOP</fixed-case>: Object-Oriented Programming Evaluation Benchmark for Large Language Models ShuaiWang LiangDing - LiShenSun Yat-Sen University + LiShenSun Yat-Sen University YongLuoWuhan University BoDuWuhan University DachengTaoUniversity of Sydney @@ -21058,7 +21058,7 @@ DuyDuong-TranUnited States Naval Academy and University of Pennsylvania, University of Pennsylvania YingDingUniversity of Texas, Austin HuanLiuArizona State University - LiShenUniversity of Pennsylvania + LiShenUniversity of Pennsylvania TianlongChen 2187-2205 Recent advancements in large language models (LLMs) have achieved promising performances across various applications. Nonetheless, the ongoing challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains. In this work, we introduce DALK, a.k.a. Dynamic Co-Augmentation of LLMs and KG, to address this limitation and demonstrate its ability on studying Alzheimer’s Disease (AD), a specialized sub-field in biomedicine and a global health priority. With a synergized framework of LLM and KG mutually enhancing each other, we first leverage LLM to construct an evolving AD-specific knowledge graph (KG) sourced from AD-related scientific literature, and then we utilize a coarse-to-fine sampling method with a novel self-aware knowledge retrieval approach to select appropriate knowledge from the KG to augment LLM inference capabilities. The experimental results, conducted on our constructed AD question answering (ADQA) benchmark, underscore the efficacy of DALK. Additionally, we perform a series of detailed analyses that can offer valuable insights and guidelines for the emerging topic of mutually enhancing KG and LLM. diff --git a/data/xml/2025.findings.xml b/data/xml/2025.findings.xml index 307833c314..9ce6403ffa 100644 --- a/data/xml/2025.findings.xml +++ b/data/xml/2025.findings.xml @@ -23144,7 +23144,7 @@ Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in <fixed-case>LLM</fixed-case>s YuchenWuShanghai Jiao Tong University LiangDing - LiShenSun Yat-Sen University + LiShenSun Yat-Sen University DachengTaoNanyang Technological University 23282-23302 Knowledge editing allows for efficient adaptation of large language models (LLMs) to new information or corrections without requiring full retraining. However, prior methods typically focus on either single-language editing or basic multilingual editing, failing to achieve true cross-linguistic knowledge synchronization. To address this, we present a simple and practical state-of-the-art (SOTA) recipe Cross-Lingual Knowledge Democracy Edit (X-KDE), designed to propagate knowledge from a dominant language to other languages effectively. Our X-KDE comprises two stages: (i) Cross-lingual Edition Instruction Tuning (XE-IT), which fine-tunes the model on a curated parallel dataset to modify in-scope knowledge while preserving unrelated information, and (ii) Target-language Preference Optimization (TL-PO), which applies advanced optimization techniques to ensure consistency across languages, fostering the transfer of updates. Additionally, we contribute a high-quality, cross-lingual dataset, specifically designed to enhance knowledge transfer across languages. Extensive experiments on the Bi-ZsRE and MzsRE benchmarks show that X-KDE significantly enhances cross-lingual performance, achieving an average improvement of +8.19%, while maintaining high accuracy in monolingual settings. diff --git a/data/yaml/name_variants.yaml b/data/yaml/name_variants.yaml index 4d1b54d9e7..13441edc1a 100644 --- a/data/yaml/name_variants.yaml +++ b/data/yaml/name_variants.yaml @@ -1160,6 +1160,14 @@ - canonical: {first: Kenneth S., last: Bøgh} variants: - {first: Kenneth, last: Bøgh} +- canonical: {first: Li, last: Shen} + id: li-shen-dartmouth + orcid: 0000-0002-5443-0503 + institution: Dartmouth College + comment: Dartmouth +- canonical: {first: Li, last: Shen} + id: li-shen + comment: May refer to several people - canonical: {first: Alena, last: Bŏhmová} variants: - {first: Alena, last: Bohmova}