Papers by Shanshan Xu
ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency (2024.emnlp-industry)
Copied to clipboard
Yuhang Yao, Han Jin, Alay Shah, Shanshan Han, Zijian Hu, Dimitris Stripelis, Yide Ran, Zhaozhuo Xu, Salman Avestimehr, Chaoyang He
| Challenge: | Large language models (LLMs) are widely used in commercial applications . low latency is crucial due to system latency, query concurrency, and computational resources constraints. |
| Approach: | They propose a system that can be resource-efficiently served by addressing bottlenecks beyond LLM inference . they propose 4.3 speed up over vLLM and 1.5 higher throughput . |
| Outcome: | The proposed system outperforms state-of-the-arts with 1.5 higher throughput . it achieves 4.3 speed up with 64 concurrent requests on Mixtral 8x7B . |
Synthesizing and Adapting Error Correction Data for Mobile Large Language Model Applications (2025.acl-industry)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have achieved impressive performance on many language tasks. |
| Approach: | They synthesize a high-quality dataset of error correction pairs to evaluate and improve LLMs for mobile applications by reweighting the sample. |
| Outcome: | The proposed model improves on offline evaluation and live A/B testing, given the LLM performance on offline data and scores from a small privacy-preserving on-device language model. |
The Craft of Selective Prediction: Towards Reliable Case Outcome Classification - An Empirical Study on European Court of Human Rights Cases (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing COC tasks prioritize high task performance over model reliability . however, large models exhibit overconfidence and Monte Carlo dropout methods produce reliable confidence estimates . |
| Approach: | They conduct an empirical investigation into how various design choices affect the reliability of COC models within the framework of selective prediction. |
| Outcome: | The proposed model is able to predict the outcome of a legal case based on the text of the case facts and is compared with other models using a pre-training corpus. |
Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for NLP calibration ignore inherent human label variation (HLV) split votes are a problem in high-stakes domains such as legal and medical decisions . |
| Approach: | They present a case outcome classification dataset with judges' vote distributions and build a taxonomy of disagreement with SV-specific subcategories. |
| Outcome: | The proposed model is compared against a judge vote distribution and assesses the alignment of perceived difficulty between models and humans. |
Position: From Noise to Signal to Selbstzweck - Reframing Human Label Variation in the Era of Post-training in NLP (2026.findings-acl)
Copied to clipboard
| Challenge: | Human Label Variation (HLV) refers to legitimate disagreement in annotation . current preference-learning datasets routinely collapse multiple annotations into a single label . |
| Approach: | They propose to preserve human label variation as an embodiment of pluralism . they argue that disagreement in annotations should be treated as a selfzweck . |
| Outcome: | The proposed approach preserves pluralism and human pluralismos, the authors argue . they argue that disagreements in annotations should be treated as a selfzweck . |
From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing work in explainable COC has been limited to annotations by a single expert. |
| Approach: | They construct a two-level task-independent taxonomy from a dataset obtained from two experts in the domain of international human rights law . they find disagreements stem from underspecification of the legal context . |
| Outcome: | The proposed dataset is the first in legal NLP that focuses on human label variation. |
CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing vision-and-language navigation methods do not incorporate environmental feedback into their decision-making processes. |
| Approach: | They propose a framework that incorporates environmental feedback into decision-making and a 3D simulator that renders realistic scenarios using Unreal Engine 5. |
| Outcome: | The proposed framework outperforms existing vision-and-language navigation methods in a zero-shot multi-task setting by 28.1% on average. |
ExtRA: Extracting Prominent Review Aspects from Customer Feedback (D18-1)
Copied to clipboard
| Challenge: | Existing methods for analyzing and summarizing customer reviews are based on a number of prominent review aspects. |
| Approach: | They propose a framework for extracting the most prominent aspects of a given product type from textual reviews. |
| Outcome: | The proposed framework extracts K most prominent aspect terms which do not overlap semantically without supervision. |
Deconfounding Legal Judgment Prediction for European Court of Human Rights Cases Towards Better Alignment with Experts (2022.emnlp-main)
Copied to clipboard
| Challenge: | Legal Judgement Prediction systems without expert-informed adjustments can be vulnerable to shallow, distracting surface signals. |
| Approach: | They propose to use domain expertise to identify statistically predictive but legally irrelevant information and adopt adversarial training to prevent it from relying on it. |
| Outcome: | The proposed model aligns better with expert rationales than baseline models . the results are compared with an existing benchmark dataset of human rights cases . |
Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding (2026.acl-long)
Copied to clipboard
Sensen Gao, Shanshan Zhao, Xu Jiang, Lunhao Duan, Yong Xien Chng, Qing-Guo Chen, Weihua Luo, Kaifu Zhang, Jia-Wang Bian, Mingming Gong
| Challenge: | Document understanding is critical for applications from financial analysis to scientific discovery. |
| Approach: | They propose a taxonomy based on domain, retrieval modality, and granularity and review advances involving graph structures and agentic frameworks. |
| Outcome: | The proposed model enables holistic retrieval and reasoning across all modalities, unlocking comprehensive document intelligence. |
QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback based Self-Correction (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for semantic parsing fail when hallucinations are encountered . QueryAgent solves a question step-by-step and performs stepwise self-correction . |
| Approach: | They propose a framework that solves a query step-by-step and performs stepwise self-correction. |
| Outcome: | The proposed framework outperforms existing methods on GrailQA and GraphQ by 5.7 and 15.0 points. |
VECHR: A Dataset for Explainable and Robust Classification of Vulnerability Type in the European Court of Human Rights (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on the concept of vulnerability at the European Court of Human Rights (ECtHR) has focused on classification and analysis of textual data. |
| Approach: | They propose to use an expert-annotated multi-label dataset to assess vulnerability in court cases. |
| Outcome: | The proposed model performs poorly on out-of-domain data and shows that it is robust. |
Extractive Summarization of Legal Decisions using Multi-task Learning and Maximal Marginal Relevance (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Summarizing legal decisions requires the expertise of law practitioners, which is time- and cost-intensive. |
| Approach: | They propose methods for extracting summarized legal decisions using limited expert annotated data. |
| Outcome: | The proposed models achieve ROUGE scores vis-à-vis expert extracted summaries that match inter-annotator comparisons. |
The Chinese Causative-Passive Homonymy Disambiguation: an adversarial Dataset for NLI and a Probing Task (2022.lrec-1)
Copied to clipboard
| Challenge: | Recent research questions whether these models really understand the meaning of natural language. |
| Approach: | They propose to transform the disambiguation of causative-passive homonymy (CPH) to a challenging natural language inference task using a pretrained transformer model RoBERTa. |
| Outcome: | The pretrained model RoBERTa performs poorly on the CANLI dataset . the model's internal representation of CPH is not captured in the model . |