Thailand

Aligning unstructured climate policy documents according to a particular classification taxonomy with little to no labeled examples is challenging and requires manual effort of climate policy researchers. In this work we examine whether large language models (LLMs) can act as an effective substitute or assist in the annotation process. Utilizing a large set of text spans from Paris Agreement Nationally Determined Contributions (NDCs) linked to United Nations Sustainable Development Goals (SDGs) and targets contained in the Climate Watch dataset from the World Resources Institute in combination with our own annotated data, we validate our approaches and establish a benchmark for model performance evaluation on this task. With our evaluation benchmarking we quantify the effectiveness of using zero-shot or few-shot prompted LLMs to align these documents.

ACL 2024

Aligning Unstructured Paris Agreement Climate Plans with Sustainable Development Goals

climate policy

prompting

workshop paper

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

Climate change poses an urgent global problem that requires efficient data analysis mechanisms to provide insights into climate-related discussions on social media platforms. This paper presents a framework aimed at understanding social media users' perceptions of various climate change topics and uncovering the insights behind these perceptions. Our framework employs large language model to develop a taxonomy of factual claims related to climate change and build a classification model that detects the truthfulness stance of tweets toward the factual claims. The findings reveal two key conclusions: (1) The public tends to believe the claims are true, regardless of the actual claim veracity; (2) The public shows a lack of discernment between facts and misinformation across different topics, particularly in areas related to politics, economy, and environment.

Granular Analysis of Social Media Users’ Truthfulness Stances Toward Climate Change Factual Claims

In the natural sciences, a common form of scholarly document is a physical sample record, which provides categorical and textual metadata for specimens collected and analyzed for scientific research. Physical sample archives like museums and repositories publish these records in data repositories to support reproducible science and enable the discovery of physical samples. However, the success of resource discovery in such interfaces depends on the completeness of the sample records. We investigate approaches for automatically completing the scientific metadata fields of sample records. We apply large language models in zero and few-shot settings and incorporate the hierarchical structure of the taxonomy. We show that a combination of record summarization, bottom-up taxonomy traversal, and few-shot prompting yield F1 as high as 0.928 on metadata completion in the Earth science domain.

Metadata Enhancement Using Large Language Models

As new research on Large Language Models LLMs continues, it is difficult to keep up with new research and models. To help researchers synthesize the new research many have written survey papers, but even those have become numerous. In this paper, we develop a method to automatically assign survey papers to a taxonomy. We collect the metadata of 144 LLMs survey papers and explore three paradigms to classify papers within the taxonomy. Our work indicates that leveraging graph structure information on co-category graphs can significantly outperform the language models in two paradigms; pre-trained language models' fine-tuning and zero-shot/few-shot classifications using LLMs. We find that our model surpasses an average human recognition level and that fine-tuning LLMs using weak labels generated by a smaller model, such as the GCN in this study, can be more effective than using ground-truth labels, revealing the potential of weak-to-strong generalization in the taxonomy classification task.

Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning

We address the challenge of interpreting and reasoning over scientific tables with Large Language Models (LLMs), a crucial aspect of scholarly documents. Despite significant progress in natural language processing, the integration of tabular data into scientific LLMs remains limited. We propose an innovative approach leveraging intermediate task pre-training on table question-answering datasets, followed by model adaptation to comprehend tables in computer science literature. Our findings reveal that incorporating table understanding substantially improves the performance of LLMs on scientific literature understanding tasks, which we showcase in peer-review score prediction. This improvement underscores the importance of utilizing tabular data in the training of scientific language models. The code and models are publicly available at https://github.com/buseskorkmaz/Integrating-Table-Representations-into-LLMs.

Integrating Table Representations into Large Language Models for Improved Scholarly Document Comprehension

This paper presents Papilusion, an AI-generated scientific text detector developed within the DAGPap24 shared task on detecting automatically generated scientific papers. We propose an ensemble-based approach and conduct ablation studies to analyze the effect of the detector configurations on the performance. Papilusion is ranked 6th on the leaderboard, and we improve our performance after the competition ended, achieving 99.46 (+9.63) of the F1-score on the official test set.

Papilusion at DAGPap24: Paper or Illusion? Detecting AI-generated Scientific Papers

We present CiteAssist, a system to automate the generation of BibTeX entries for preprints, streamlining the process of bibliographic annotation. Our system extracts metadata, such as author names, titles, publication dates, and keywords, to create standardized annotations within the document. CiteAssist automatically attaches the BibTeX citation to the end of a PDF and links it on the first page of the document so other researchers gain immediate access to the correct citation of the article. This method promotes platform flexibility by ensuring that annotations remain accessible regardless of the repository used to publish or access the preprint. The annotations remain available even if the preprint is viewed externally to CiteAssist. Additionally, the system adds relevant related papers based on extracted keywords to the preprint, providing researchers with additional publications besides those in related work for further reading. Researchers can enhance their preprints organization and reference management workflows through a free and publicly available web interface.

CiteAssist: A System for Automated Preprint Citation and BibTeX Generation

Knowing whether scientific claims are supported by evidence is fundamental to scholarly communication and evidence-based decision-making. We present our approach to Task 1 of the Context24 Shared Task---Contextualizing Scientific Figures and Tables (SDP@ACL2024), which focuses on identifying multimodal evidence from scientific publications that support claims. We finetune CLIP, a state-of-the-art model for image-text similarity tasks, to identify and rank figures and tables in papers that substantiate specific claims. Our methods focus on text and image preprocessing techniques and augmenting the organizer-provided training data with labeled examples from the SciMMIR and MedICaT datasets. Our best-performing model achieved NDCG@5 and NDCG@10 values of 0.26 and 0.30, respectively, on the Context24 test split. Our findings underscore the effectiveness of data augmentation and preprocessing in improving the model's ability in evidence matching.

Harnessing CLIP for Evidence Identification in Scientific Literature: A Multimodal Approach to Context24 Shared Task

Identifying the alignment between different parts of a scientific paper is fundamental to scholarly document processing. In the Context24 shared task, participants are given a scientific claim and asked to identify (1) key figures or tables that support the claim and (2) methodological details. While employing a supervised approach to train models on task-specific data is a prevailing strategy for both subtasks, such an approach is not feasible for low-resource domains. Therefore, this paper introduces data-free systems supported by Large Language Models. We propose systems based on GPT-4o and GPT-4-turbo for each task. The experimental results reveal the zero-shot capabilities of GPT-4* in both tasks.

OSX at Context24: How Well Can GPT Tackle Contexualizing Scientific Figures and Tables

Author affiliation information plays a key role in bibliometric analyses and is essential for evaluating studies. However, as author affiliation information has not been standardized, which leads to difficulties such as synonym ambiguity and incomplete data during automated processing. To address the challenge, this paper proposes an end-to-end entity recognition and disambiguation framework for identifying author affiliation from literature publications. For entity disambiguation, an algorithm combining word embedding and spatial embedding is presented considering that author affiliation texts often contain rich geographic information. The disambiguation algorithm utilizes the semantic information and geographic information, which effectively enhances entity recognition and disambiguation effect. In addition, the proposed framework facilitates the effective utilization of the extensive literature in the PubMed database for comprehensive bibliometric analysis. The experimental results verify the robustness and effectiveness of the algorithm.

An end-to-end entity recognition and disambiguation framework for identifying Author Affiliation from literature publications

Large Language Models (LLMs) have shown remarkable potential across various domains, yet their application in addressing complex scientific problems remains a formidable challenge. This paper presents a novel methodology to augment the problem-solving capabilities of LLMs by assigning them roles as domain-specific experts. By simulating a panel of experts, each LLM is tasked with delivering professional and cautious responses to scientific inquiries. Our approach involves querying multiple LLMs and assessing the consistency of their responses. High agreement among the LLMs suggests greater confidence in the proposed solution, whereas discrepancies prompt a collaborative discussion among the LLMs to reach a consensus. This method emulates real-world scientific problem-solving processes, fostering a more reliable and robust mechanism for LLMs to tackle scientific questions. Our experimental results show that assigning roles to multiple LLMs as domain-specific experts significantly improves their accuracy and reliability in solving scientific problems. This framework has the potential to advance the application of AI in scientific research, enhancing its effectiveness and trustworthiness.

Premium content

Aligning Unstructured Paris Agreement Climate Plans with Sustainable Development Goals

Next from ACL 2024

Granular Analysis of Social Media Users’ Truthfulness Stances Toward Climate Change Factual Claims

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES