Upload README.md

README.md

@@ -18,9 +18,9 @@ adversarial edits that defeat most detectors: homoglyph substitution, zero-width
 character insertion, whitespace and typographic attacks.
 
 It is the system reported in our AACL-IJCNLP 2026 main-conference paper. The
-finding behind it: normalising the **training** corpus deduplicates it — 35.4% of
+finding behind it: normalising the **training** corpus deduplicates it (35.4% of
 RAID rows collapse into byte-identical copies of their clean siblings, deleting
-the adversarial supervision — while normalising at **inference** is an effective
+the adversarial supervision), while normalising at **inference** is an effective
 defence. DeBERTa-ConPara trains on raw text and normalises only at inference.
 
 - **Architecture:** DeBERTa-v3-large → CLS token → Linear(1024, 512) → GELU →
@@ -39,7 +39,7 @@ Cross-dataset, balanced accuracy at one threshold calibrated on our source
 validation split and held fixed: HC3-QA 99.69, HC3-SI 83.50, MAGE 96.23,
 M4 98.27.
 
-The README of the [GitHub repository](https://github.com/MohamedMady19/deberta-conpara)
+The README of the [GitHub repository](https://github.com/SES-Lab-OTH/deberta-conpara)
 compares DeBERTa-ConPara with every RAID leaderboard system that publishes a checkpoint,
 and states the two caveats those numbers need: MELD scores higher than DeBERTa-ConPara
 on RAID itself, and HC3/MAGE/M4 are training sources for DeBERTa-ConPara while being
@@ -64,7 +64,7 @@ detector robust to homoglyph and zero-width attacks.
 
 ## Intended use and limits
 
-Intended as **supporting evidence for a human decision** — flagging text for
+Intended as **supporting evidence for a human decision**: flagging text for
 review, studying detector behaviour, benchmarking. Not intended as a verdict, and
 not suitable for disciplinary or hiring decisions about individuals.
 
@@ -92,12 +92,18 @@ reproducible from `evaluation/`.
 
 ```bibtex
 @inproceedings{mady2026conpara,
-  title     = {Where You Normalise Matters: Unicode Preprocessing and the
-               Robustness of AI-Generated Text Detection},
-  author    = {Mady, Mohamed and Li, Yupei and Reschke, Johannes and Schuller, Bj\"orn W.},
-  booktitle = {Proceedings of AACL-IJCNLP 2026},
-  year      = {2026},
-  note      = {To appear}
+  title         = {{DeBERTa-ConPara}: Attack-Aware and Deployment-Realistic
+                   Detection of {AI}-Generated Text},
+  author        = {Mady, Mohamed and Li, Yupei and Reschke, Johannes and Schuller, Bj\"orn W.},
+  booktitle     = {Proceedings of the 14th International Joint Conference on Natural
+                   Language Processing and the 4th Conference of the Asia-Pacific Chapter
+                   of the Association for Computational Linguistics (AACL-IJCNLP 2026)},
+  year          = {2026},
+  publisher     = {Association for Computational Linguistics},
+  eprint        = {2610.00883},
+  archivePrefix = {arXiv},
+  primaryClass  = {cs.CL},
+  url           = {https://arxiv.org/abs/2610.00883}
 }
 ```
 
@@ -105,6 +111,7 @@ License: MIT, matching the DeBERTa-v3-large backbone.
 
 ## Links
 
-- Code and evaluation scripts: https://github.com/MohamedMady19/deberta-conpara
+- Code and evaluation scripts: https://github.com/SES-Lab-OTH/deberta-conpara
 - Live demo: https://huggingface.co/spaces/mohamedmady/deberta-conpara
-- Paper: "DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text", AACL-IJCNLP 2026 (arXiv link to follow)
+- Paper: "DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text", AACL-IJCNLP 2026, [arXiv:2610.00883](https://arxiv.org/abs/2610.00883)
+- Lab: [Smart Embedded Systems Lab, OTH Regensburg](https://github.com/SES-Lab-OTH)