Papers with SAR
Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversation (N19-1)
Copied to clipboard
| Challenge: | asynchronous domains lack large labeled datasets to train an effective speech act recognition model. |
| Approach: | They propose methods to leverage abundant unlabeled conversational data and available labeled data from synchronous domains to train an effective SAR model. |
| Outcome: | The proposed method outperforms existing methods when trained on in-domain data only. |
Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks (2023.eacl-main)
Copied to clipboard
| Challenge: | Statutory article retrieval (SAR) is a promising application of legal text processing. |
| Approach: | They propose a graph-augmented dense statute retriever model that incorporates the structure of legislation via a neural network to improve density retrieval performance. |
| Outcome: | The proposed model outperforms baselines on a real-world expert-annotated dataset. |
JuriFindIT: an Italian legal retrieval dataset (2026.findings-eacl)
Copied to clipboard
| Challenge: | Statutory article retrieval (SAR) targets retrieval of legislative provisions relevant to a natural language question. |
| Approach: | They propose a pipeline that integrates dense encoders with an heterogeneous legislative graph . they propose statutory article retrieval (SAR) is the first SAR dataset for the italian legal domain . |
| Outcome: | The proposed pipeline improves over existing approaches. |
MCLE-Mol: Empowering LLM with Molecular Comprehension and Low-Cost Continual Evolution for Interpretable Property Prediction (2026.findings-acl)
Copied to clipboard
Zhili Pu, Lantian Zhang, Hao Duan, Zhixing Zhang, Keyun Zhu, Yongqi Fan, Ruihui Hou, Tong Ruan, Yun Tang
| Challenge: | Large language models (LLMs) offer a new paradigm for molecular property prediction (MPP), yet a semantic gap between natural language and molecul representations limits their ability to capture structure–activity relationships (SAR). |
| Approach: | They propose an ML–LLM–Rule collaborative framework for MPP that injects ML-derived substructure attribution values into LLMs and calibrates them under specific chemical contexts. |
| Outcome: | The proposed framework outperforms baseline models on multiple benchmark datasets and is highly interpretable. |
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models (2024.acl-long)
Copied to clipboard
Jinhao Duan, Hao Cheng, Shiqi Wang, Alex Zavalny, Chenan Wang, Renjing Xu, Bhavya Kailkhura, Kaidi Xu
| Challenge: | Large Language Models (LLMs) show promising results in language generation but often “hallucinate”, making their outputs less reliable. |
| Approach: | They propose to shift attention to more relevant components at token- and sentence-levels for better UQ. |
| Outcome: | The proposed approach improves the performance of a range of popular “off-the-shelf” LLMs with model sizes extending up to 33B parameters. |
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods neglect stylistic modeling and rely on static thresholds, which greatly limits the detection performance. |
| Approach: | They propose a framework that enables stylistics-aware uncertainty quantification through conditional threshold estimation. |
| Outcome: | The proposed framework achieves an average improvement 11.34% in detection performance compared to baselines. |
Check It Again:Progressive Visual Question Answering via Visual Entailment (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to Visual Question Answering (VQA) only address superficial correlations between image and answer. |
| Approach: | They propose a select-and-rerank progressive framework based on Visual Entailment to address this problem. |
| Outcome: | The proposed framework improves on the Visual Question Answering (VQA) task with 7.55% accuracy. |
CuSINeS: Curriculum-driven Structure Induced Negative Sampling for Statutory Article Retrieval (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to assess Statutory Article Retrieval (SAR) are vague and underspecified, resulting in a lack of clarity and a gap between legal expertise and public comprehension. |
| Approach: | They propose a negative sampling approach to enhance the performance of Statutory Article Retrieval (SAR) it employs a curriculum-based negative sampling strategy guiding the model to focus on easier negatives initially and progressively tackle more difficult ones. |
| Outcome: | The proposed approach surpasses static methods and can be used to assess the difficulty of the model. |
Adaptive Contrastive Knowledge Distillation for BERT Compression (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge distillation methods for BERT implicitly learn discriminative student features by mimicking the teacher features. |
| Approach: | They propose a new knowledge distillation approach called adaptive contrastive knowledge distilling for BERT compression using hidden state features in BERT as explicit supervision to learn discriminative student features. |
| Outcome: | The proposed approach improves on multiple natural language processing tasks. |