Papers with NeurIPS
AutoML for NLP (2023.eacl-tutorials)
Copied to clipboard
| Challenge: | Automated Machine Learning (AutoML) is an emerging field that has potential to impact how we build models in NLP. |
| Approach: | This tutorial will summarize the main AutoML techniques and illustrate how to apply them to improve the NLP model-building process. |
| Outcome: | This tutorial summarizes the main AutoML techniques and illustrates how to apply them to improve the model-building process. |
Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can help in citation generation but can also amplify existing biases, such as the Matthew effect, and introduce new ones, potentially skewing scientific knowledge dissemination. |
| Approach: | They propose to use large language models to generate scholarly references for in-text citations in papers published after GPT-4's knowledge cut-off date. |
| Outcome: | The proposed model can generate scholarly references for in-text citations, but without the aid of web browsing or a search engine, the results show a similarity between human and LLM citation patterns, but with a more pronounced high citation bias. |
BAGELS: Benchmarking the Automated Generation and Extraction of Limitations from Scholarly Text (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a growing number of scientific publications have limitations as a source of uncertainty. |
| Approach: | They propose a computational architecture for extracting and generating limitations from scholarly papers using a novel Retrieval Augmented Generation technique. |
| Outcome: | The proposed architecture extracts limitations from ACL, NeurIPS, and PeerJ papers and supplementes them with external reviews. |