What an incredible EMNLP experience — truly the most fulfilling conference I’ve ever attended!
✅ Oral presentation
✅ SAC Highlights Award
✅ Panel discussion
Grateful to my amazing collaborators and to all the friends I had the chance to meet! 🌟
#EMNLP2025 #NLP
Detailed programme now up on website. Looking forward to 14 research papers, results of the 3rd Shared Task on Learning with Disagreements (LeWiDi), a talk from @camachocollados.bsky.social, and a panel discussion feat. Jose, Eve Fleisig, and @beiduo.bsky.social. See you in Room A305 or online!
Instead of unnatural post-hoc explanations, we look forward. A model's CoT already contains rationales for all options. We introduce CoT2EL, a pipeline that uses linguistic discourse segmenters to extract these high-quality, faithful units to explore human label variation.
Matching exact probabilities for HLV is unstable. So, we propose a more robust rank-based evaluation that checks preference order. Our combined method outperforms baselines on 3 datasets that exhibit human label variation, showing it better aligns with diverse human perspectives.
📑 Our CoT2EL paper will be presented as an oral at #EMNLP2025 in Suzhou!
Humans often disagree on labels. Can a model's own reasoning (CoT) help us understand why? We developed a new method to extract these insights. Come join us!
🗓️ Friday, Nov 7, 14:00 - 15:30
📍 Room: A110
