Papers with nDCG
A Submodular Feature-Aware Framework for Label Subset Selection in Extreme Classification Problems (N19-1)
Copied to clipboard
| Challenge: | Experimental results show that extreme multi-label learning improves label prediction quality by 3% to 5% in three of the 5 tasks and is competitive in the others. |
| Approach: | They propose a submodular maximization framework with linear cost to find informative labels which are most relevant to other labels yet least redundant with each other. |
| Outcome: | The proposed model improves label prediction quality by 3% to 5% in three of the 5 tasks and is competitive in the others. |
IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing dense retrieval methods rely on static embeddings that obscure bidirectional relationship between queries and documents. |
| Approach: | They propose a framework that augments any black-box dense retrievers with dynamic, bidirectional modulation at inference time. |
| Outcome: | a new framework augments any dense retriever with dynamic, bidirectional modulation at inference time. |
Redefining Retrieval Evaluation in the Era of LLMs (2026.eacl-long)
Copied to clipboard
| Challenge: | Traditional IR metrics assume that humans examine documents sequentially with diminishing attention to lower ranks. |
| Approach: | They propose a utility-based annotation schema that quantifies positive contribution of relevant passages and negative impact of distracting ones. |
| Outcome: | The proposed metric improves correlation with the end-to-end answer accuracy by up to 36% compared to traditional metrics. |
ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to model resume-job fit are sparse since job seekers apply to only a few jobs. |
| Approach: | They propose two techniques to enhance the encoder’s contrastive training process by augmenting job data with hypothetical reference resume generated by a large language model and creating high-quality hard negatives from unlabeled resume/job pairs using a novel hard-negative mining strategy. |
| Outcome: | The proposed method outperforms ConFit and prior methods on two real-world datasets and achieves an average improvement of 13.8% in recall and 17.5% in nDCG across job-ranking and resume-ranker tasks. |
HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for table-text retrieval are limited due to the need to bridge structured tables and unstructured passages. |
| Approach: | They propose a table-text retrieval system that combines the strengths of both approaches . they propose bipartite subgraph retrieval and query-relevant node expansion . |
| Outcome: | The proposed method outperforms state-of-the-art models with a 42.6% and 39.9% improvement on the OTT-QA benchmark. |