updated README

README.md

@@ -8,7 +8,7 @@ pinned: false
 license: cc-by-sa-4.0
 ---
 
-# Welcome to RLHN
+# Welcome to RLHN (EMNLP 2025 Findings)
 RLHN (ReLabeing Hard Negatives) uses a cascading LLM framework to identify and relabel *false negatives* in IR training datasets.
 
 This repository contains training datasets curated by RLHN \& models fine-tuned on these curated datasets.
@@ -19,18 +19,30 @@ List of Contributors:
 - Xueguang Ma
 - Jimmy Lin
 
-Preprint URL: https://huggingface.co/papers/2505.16967
+Paper URL: https://aclanthology.org/2025.findings-emnlp.481/
 
 # Citation
 
 ```
-@misc{thakur2025rlhn,
-      title={Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval}, 
-      author={Nandan Thakur and Crystina Zhang and Xueguang Ma and Jimmy Lin},
-      year={2025},
-      eprint={2505.16967},
-      archivePrefix={arXiv},
-      primaryClass={cs.IR},
-      url={https://arxiv.org/abs/2505.16967}, 
+@inproceedings{thakur-etal-2025-hard,
+    title = "Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with {LLM}s",
+    author = "Thakur, Nandan  and
+      Zhang, Crystina  and
+      Ma, Xueguang  and
+      Lin, Jimmy",
+    editor = "Christodoulopoulos, Christos  and
+      Chakraborty, Tanmoy  and
+      Rose, Carolyn  and
+      Peng, Violet",
+    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
+    month = nov,
+    year = "2025",
+    address = "Suzhou, China",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/2025.findings-emnlp.481/",
+    doi = "10.18653/v1/2025.findings-emnlp.481",
+    pages = "9064--9083",
+    ISBN = "979-8-89176-335-7",
+    abstract = "Training robust retrieval and reranker models typically relies on large-scale retrieval datasets; for example, the BGE collection contains 1.6 million query-passage pairs sourced from various data sources. However, we find that certain datasets can negatively impact model effectiveness {---} pruning 8 out of 15 datasets from the BGE collection, reduces the training set size by 2.35{\texttimes}, surprisingly increases nDCG@10 on BEIR by 1.0 point. This motivates a deeper examination of training data quality, with a particular focus on ``false negatives'', where relevant passages are incorrectly labeled as irrelevant. We utilize LLMs as a simple, cost-effective approach to \textit{identify} and \textit{relabel} false negatives in training datasets. Experimental results show that relabeling false negatives as true positives improves both E5 (base) and Qwen2.5-7B retrieval models by 0.7-1.4 points on BEIR and by 1.7-1.8 points at nDCG@10 on zero-shot AIR-Bench evaluation. Similar gains are observed for rerankers fine-tuned on the relabeled data, such as Qwen2.5-3B on BEIR. The reliability of LLMs to identify false negatives is supported by human annotation results. Our training dataset and code are publicly available."
 }
 ```