diff --git a/data/xml/2021.emnlp.xml b/data/xml/2021.emnlp.xml
index e7faac1620..3d005dc55e 100644
--- a/data/xml/2021.emnlp.xml
+++ b/data/xml/2021.emnlp.xml
@@ -2827,7 +2827,7 @@
Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification
PengfeiCao
YuboChen
- YuqingYang
+ YuqingYang
KangLiu
JunZhao
2636–2645
diff --git a/data/xml/2022.findings.xml b/data/xml/2022.findings.xml
index 531b154935..229371d8f0 100644
--- a/data/xml/2022.findings.xml
+++ b/data/xml/2022.findings.xml
@@ -11467,7 +11467,7 @@ Faster and Smaller Speech Translation without Quality Compromise
DORE: Document Ordered Relation Extraction based on Generative Framework
QipengGuoAmazon Shanghai AI Lab
- YuqingYangFudan University
+ YuqingYangFudan University
HangYanFudan University
XipengQiuFudan University
ZhengZhangNYU Shanghai
diff --git a/data/xml/2023.acl.xml b/data/xml/2023.acl.xml
index 21f2770765..841f1c3bb8 100644
--- a/data/xml/2023.acl.xml
+++ b/data/xml/2023.acl.xml
@@ -10376,7 +10376,7 @@
An AMR-based Link Prediction Approach for Document-level Event Argument Extraction
- YuqingYangFudan University
+ YuqingYangFudan University
QipengGuoAmazon Shanghai AI Lab
XiangkunHuAmazon
YueZhangWestlake University
diff --git a/data/xml/2023.emnlp.xml b/data/xml/2023.emnlp.xml
index e10b1210a6..b95a6e7519 100644
--- a/data/xml/2023.emnlp.xml
+++ b/data/xml/2023.emnlp.xml
@@ -2379,7 +2379,7 @@
Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts
TengxiaoLiu
QipengGuo
- YuqingYang
+ YuqingYang
XiangkunHu
YueZhang
XipengQiu
@@ -11496,7 +11496,7 @@
HuiqiangJiang
QianhuiWu
Chin-YewLin
- YuqingYang
+ YuqingYang
LiliQiu
13358-13376
Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts fed to LLMs are becoming increasingly lengthy, even exceeding tens of thousands of tokens. To accelerate model inference and reduce cost, this paper presents LLMLingua, a coarse-to-fine prompt compression method that involves a budget controller to maintain semantic integrity under high compression ratios, a token-level iterative compression algorithm to better model the interdependence between compressed contents, and an instruction tuning based method for distribution alignment between language models. We conduct experiments and analysis over four datasets from different scenarios, i.e., GSM8K, BBH, ShareGPT, and Arxiv-March23; showing that the proposed approach yields state-of-the-art performance and allows for up to 20x compression with little performance loss.
@@ -15516,7 +15516,7 @@ The experiments were repeated and the tables and figures were updated. Changes a
JiaweiHongFudan University
KeyuChenFudan University
XiaoranLiuFudan University
- YuqingYangFudan University
+ YuqingYangFudan University
HonglinGuoFudan University
TengxiaoLiuFudan University
YuSunFudan University
diff --git a/data/xml/2024.acl.xml b/data/xml/2024.acl.xml
index 6a03746558..f4325d1e88 100644
--- a/data/xml/2024.acl.xml
+++ b/data/xml/2024.acl.xml
@@ -1287,7 +1287,7 @@
XufangLuoMicrosoft Research
DongshengLi
Chin-YewLinMicrosoft
- YuqingYangResearch, Microsoft
+ YuqingYangResearch, Microsoft
LiliQiuMicrosoft
1658-1677
In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key information in the input prompt. Inspired by these findings, we propose LongLLMLingua for prompt compression towards improving LLMs’ perception of the key information to simultaneously address the three challenges. Our extensive evaluation across various long context scenarios demonstrates that LongLLMLingua not only enhances performance but also significantly reduces costs and latency. For instance, in the NaturalQuestions benchmark, LongLLMLingua boosts performance by up to 21.4% with around 4x fewer tokens in GPT-3.5-Turbo, leading to substantial cost savings. It achieves a 94.0% cost reduction in the LooGLE benchmark. Moreover, when compressing prompts of about 10k tokens at ratios of 2x-6x, LongLLMLingua can accelerate end-to-end latency by 1.4x-2.6x.
@@ -4308,7 +4308,7 @@
QiyangJiangShanghaiTech University
XingyuHanXingyuHan
NanChenMicrosoft
- YuqingYangResearch, Microsoft
+ YuqingYangResearch, Microsoft
KanRenShanghaiTech University
5677-5700
In the era of data-driven decision-making, the complexity of data analysis necessitates advanced expertise and tools of data science, presenting significant challenges even for specialists. Large Language Models (LLMs) have emerged as promising aids as data science agents, assisting humans in data analysis and processing. Yet their practical efficacy remains constrained by the varied demands of real-world applications and complicated analytical process. In this paper, we introduce DSEval – a novel evaluation paradigm, as well as a series of innovative benchmarks tailored for assessing the performance of these agents throughout the entire data science lifecycle. Incorporating a novel bootstrapped annotation method, we streamline dataset preparation, improve the evaluation coverage, and expand benchmarking comprehensiveness. Our findings uncover prevalent obstacles and provide critical insights to inform future advancements in the field.
@@ -6158,7 +6158,7 @@
Full Parameter Fine-tuning for Large Language Models with Limited Resources
KaiLv
- YuqingYang
+ YuqingYang
TengxiaoLiuFudan University and Amazon
QipengGuoShanghai AI Laboratory
XipengQiuFudan University
diff --git a/data/xml/2024.eacl.xml b/data/xml/2024.eacl.xml
index 46c180c795..6ea11d0858 100644
--- a/data/xml/2024.eacl.xml
+++ b/data/xml/2024.eacl.xml
@@ -2455,7 +2455,7 @@
YugeZhangMicrosoft
KanRenMicrosoft
DongshengLi
- YuqingYangResearch, Microsoft
+ YuqingYangResearch, Microsoft
2931-2959
The field of machine learning (ML) has gained widespread adoption, leading to significant demand for adapting ML to specific scenarios, which is yet expensive and non-trivial. The predominant approaches towards the automation of solving ML tasks (e.g., AutoML) are often time-consuming and hard to understand for human developers. In contrast, though human engineers have the incredible ability to understand tasks and reason about solutions, their experience and knowledge are often sparse and difficult to utilize by quantitative approaches. In this paper, we aim to bridge the gap between machine intelligence and human knowledge by introducing a novel framework MLCopilot, which leverages the state-of-the-art large language models to develop ML solutions for novel tasks. We showcase the possibility of extending the capability of LLMs to comprehend structured inputs and perform thorough reasoning for solving novel ML tasks. And we find that, after some dedicated design, the LLM can (i) observe from the existing experiences of ML tasks and (ii) reason effectively to deliver promising results for new tasks. The solution generated can be used directly to achieve high levels of competitiveness.
2024.eacl-long.179
diff --git a/data/xml/2024.emnlp.xml b/data/xml/2024.emnlp.xml
index 2c32db9d75..f9b0d1148e 100644
--- a/data/xml/2024.emnlp.xml
+++ b/data/xml/2024.emnlp.xml
@@ -5875,7 +5875,7 @@
ZhiyuanHeMicrosoft
HuiqiangJiangMicrosoft
ZilongWangMicrosoft Research
- YuqingYangResearch, Microsoft
+ YuqingYangResearch, Microsoft
Luna K.QiuMicrosoft
LiliQiuMicrosoft
7333-7345
diff --git a/data/xml/2024.findings.xml b/data/xml/2024.findings.xml
index 3892c3c698..cf5927fef7 100644
--- a/data/xml/2024.findings.xml
+++ b/data/xml/2024.findings.xml
@@ -6904,7 +6904,7 @@
JueZhangMicrosoft
QingweiLinMicrosoft Research
VictorRühleMicrosoft
- YuqingYangResearch, Microsoft
+ YuqingYangResearch, Microsoft
Chin-YewLinMicrosoft
H. VickyZhaoTsinghua University, Tsinghua University
LiliQiuMicrosoft
@@ -26114,7 +26114,7 @@ and high variation in performance on the subset, suggesting our plausibility cri
Weak-to-Strong Reasoning
- YuqingYangUniversity of Southern California
+ YuqingYangUniversity of Southern California
YanMa
PengfeiLiu
8350-8367
@@ -29668,7 +29668,7 @@ hai-coaching/
FangyunWei
ZongqingLuTsinghua University, Tsinghua University
LiliQiuMicrosoft
- YuqingYangResearch, Microsoft
+ YuqingYangResearch, Microsoft
12806-12816
Efficient fine-tuning plays a fundamental role in modern large models, with low-rank adaptation emerging as a particularly promising approach. However, the existing variants of LoRA are hampered by limited expressiveness, a tendency to overfit, and sensitivity to hyperparameter settings. This paper presents LoRA Slow Cascade Learning (LoRASC), an innovative technique designed to enhance LoRA’s expressiveness and generalization capabilities while preserving its training efficiency. Our approach augments expressiveness through a cascaded learning strategy that enables a mixture-of-low-rank adaptation, thereby increasing the model’s ability to capture complex patterns. Additionally, we introduce a slow-fast update mechanism and cascading noisy tuning to bolster generalization. The extensive experiments on various language and vision datasets, as well as robustness benchmarks, demonstrate that the proposed method not only significantly outperforms existing baselines, but also mitigates overfitting, enhances model stability, and improves OOD robustness.
2024.findings-emnlp.748
diff --git a/data/xml/2025.emnlp.xml b/data/xml/2025.emnlp.xml
index 42db134827..dabcb3dcaf 100644
--- a/data/xml/2025.emnlp.xml
+++ b/data/xml/2025.emnlp.xml
@@ -23272,7 +23272,7 @@
ZhiyuanHeMicrosoft
HuiqiangJiangMicrosoft
ChengruidongZhangMicrosoft
- YuqingYangResearch, Microsoft
+ YuqingYangResearch, Microsoft
JianyongWangTsinghua University, Tsinghua University
LiliQiuMicrosoft and University of Texas at Austin
31110-31125
diff --git a/data/xml/2025.findings.xml b/data/xml/2025.findings.xml
index 2860571e62..d4282a138f 100644
--- a/data/xml/2025.findings.xml
+++ b/data/xml/2025.findings.xml
@@ -10848,7 +10848,7 @@
QianhuiWuMicrosoft
Chin-YewLinMicrosoft
DongshengLiMicrosoft Research Asia
- YuqingYangResearch, Microsoft
+ YuqingYangResearch, Microsoft
YongfengHuangTsinghua University, Tsinghua University
LiliQiuMicrosoft and University of Texas at Austin
6092-6111
@@ -29842,7 +29842,7 @@
JiachengLi
Zoupanxiang
YudongZhouPriorShape and Richinfo
- YuqingYang
+ YuqingYang
5069-5081
This study investigates the position bias in information retrieval, where models tend to overemphasize content at the beginning of passages while neglecting semantically relevant information that appears later. To analyze the extent and impact of position bias, we introduce a new evaluation framework consisting of two position-aware retrieval benchmarks (SQuAD-PosQ, FineWeb-PosQ) and an intuitive diagnostic metric, the Position Sensitivity Index (PSI), for quantifying position bias from a worst-case perspective. We conduct a comprehensive evaluation across the full retrieval pipeline, including BM25, dense embedding models, ColBERT-style late-interaction models, and full-interaction reranker models. Our experiments show that when relevant information appears later in the passage, dense embedding models and ColBERT-style models suffer significant performance degradation (an average drop of 15.6%). In contrast, BM25 and reranker models demonstrate greater robustness to such positional variation. These findings provide practical insights into model sensitivity to the position of relevant information and offer guidance for building more position-robust retrieval systems. Code and data are publicly available at: https://github.com/NovaSearch-Team/position-bias-in-IR.
2025.findings-emnlp.271
diff --git a/data/yaml/name_variants.yaml b/data/yaml/name_variants.yaml
index 430e06b50f..b7ebb2d93f 100644
--- a/data/yaml/name_variants.yaml
+++ b/data/yaml/name_variants.yaml
@@ -605,6 +605,14 @@
- canonical: {first: François, last: Barthélemy}
variants:
- {first: Francois, last: Barthelemy}
+- canonical: {first: Yuqing, last: Yang}
+ id: yuqing-yang-usc
+ orcid: 0009-0006-7205-1191
+ institution: University of Southern California
+ comment: USC
+- canonical: {first: Yuqing, last: Yang}
+ id: yuqing-yang
+ comment: May refer to several people
- canonical: {first: G. Edward, last: Barton}
variants:
- {first: G. Edward, last: 'Barton, Jr.'}