Papers with ROC-AUC
RTSM: Knowledge Distillation with Diverse Signals for Efficient Real-Time Semantic Matching in E-Commerce (2025.naacl-industry)
Copied to clipboard
| Challenge: | e-commerce product search is a key component of product discovery and sales in ecommerce . high computational demands of large transformer models pose challenges for their deployment in real-time scenarios. |
| Approach: | They propose a framework for real-time semantic matching that leverages both soft labels from a teacher model and ground truth generated from pairwise query-product and query-query signals. |
| Outcome: | The proposed framework outperforms teacher models and state-of-the-art models on e-commerce datasets. |
Forum 4.0: An Open-Source User Comment Analysis Framework (2021.eacl-demos)
Copied to clipboard
Marlo Haering, Jakob Smedegaard Andersen, Chris Biemann, Wiebke Loosen, Benjamin Milde, Tim Pietz, Christian Stöcker, Gregor Wiedemann, Olaf Zukunft, Walid Maalej
| Challenge: | Using Forum 4.0, we analyze, aggregate, and visualize user comments based on labels defined by domain experts. |
| Approach: | They introduce an open-source framework to semi-automatically analyze, aggregate, and visualize user comments based on labels defined by domain experts. |
| Outcome: | The proposed framework can analyze, aggregate, and visualize user comments based on labels defined by domain experts. |
KD-Boost: Boosting Real-Time Semantic Matching in E-commerce with Knowledge Distillation (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Existing SOTA techniques for semantic matching are mostly based on Siamese networks. |
| Approach: | They propose a novel knowledge distillation algorithm designed for real-time semantic matching . they train low latency accurate student models by leveraging soft labels from a teacher model . |
| Outcome: | The proposed algorithm outperforms teacher and SOTA knowledge distillation benchmarks on e-commerce datasets. |
Unsupervised Detection of LLM-Generated Text in Korean Using Syntactic and Semantic Cues (2026.findings-eacl)
Copied to clipboard
| Challenge: | Prior work focused on English, leaving low-resource languages such as Korean underexplored. |
| Approach: | They propose an unsupervised framework that integrates syntactic token cohesiveness and semantic regeneration similarity to detect Korean text. |
| Outcome: | The proposed framework outperforms baselines in Korean and other low-resource languages without training. |
Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for fact checking RAG outputs rely on large language models. |
| Approach: | They propose a method that computes a factuality score that can be thresholded to yield a binary decision to check RAG outputs. |
| Outcome: | The proposed method is low latency and low cost at run-time and no need for LLM fine-tuning. |
Automatic Identification of COVID-19-Related Conspiracy Narratives in German Telegram Channels and Chats (2024.lrec-main)
Copied to clipboard
Philipp Heinrich, Andreas Blombach, Bao Minh Doan Dang, Leonardo Zilio, Linda Havenstein, Nathan Dykes, Stephanie Evert, Fabian Schäfer
| Challenge: | Existing methods to identify and track conspiracy narratives are difficult to track and use because of their short-lived nature. |
| Approach: | They analysed 1,000 German Telegram posts tagged with 14 fine-grained conspiracy narrative labels by three independent annotators. |
| Outcome: | The proposed methods compare well with off-the-shelf methods and human performance. |
Combining Psychological Theory with Language Models for Suicide Risk Detection (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing models for suicide prevention are limited in domains and are not available in low-resource languages. |
| Approach: | They propose a computational model that combines pre-trained language models with a fixed set of manually crafted suicidal cues and a two-stage fine-tuning process to detect suicide risk. |
| Outcome: | The proposed model outperforms baseline models even early on in the conversation and performs well across genders and age groups. |
Detecting Suicide Risk in Online Counseling Services: A Study in a Low-Resource Language (2022.coling-1)
Copied to clipboard
| Challenge: | Existing domain-specific models for detecting suicide are lacking in low-resource languages. |
| Approach: | They propose a model that combines pre-trained language models with a fixed set of suicidal cues and a two-stage fine-tuning process to detect SI. |
| Outcome: | The proposed model outperforms baseline models even early on in the conversation and performs well across genders and age groups. |
Temporal Flattening in LLM-Generated Text: Comparing Human and LLM Writing Trajectories (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly used in daily applications, from content generation to code writing. |
| Approach: | They construct a longitudinal dataset of 412 human authors and 6,086 documents spanning 2012–2024 and compare them to trajectories generated by three representative LLMs. |
| Outcome: | The results show that LLMs produce greater lexical diversity but exhibit substantially reduced semantic and cognitive–emotional drift relative to humans. |