United States

Climate change (CC) has attracted increasing attention in NLP in recent years. However, detecting the stance on CC in multimodal data is understudied and remains challenging due to a lack of reliable datasets. To improve the understanding of public opinions and communication strategies, this paper presents MultiClimate, the first open-source manually-annotated stance detection dataset with $100$ CC-related YouTube videos and $4,209$ frame-transcript pairs. We deploy state-of-the-art vision and language models, as well as multimodal models for MultiClimate stance detection. Results show that text-only BERT significantly outperforms image-only ResNet50 and ViT. Combining both modalities achieves state-of-the-art, $0.747$/$0.749$ in accuracy/F1. Our 100M-sized fusion models also beat CLIP and BLIP, as well as the much larger 9B-sized multimodal IDEFICS and text-only Llama3 and Gemma2, indicating that multimodal stance detection remains challenging for large language models. Our code, dataset, as well as supplementary materials, are available at https://github.com/werywjw/MultiClimate.

EMNLP 2024

MultiClimate: Multimodal Stance Detection on Climate Change Videos

multimodal models

large language models

stance detection

climate change

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

## Welcome to EMNLP 2024! 
We are excited to welcome you to one of the most prominent conferences in the field of Natural Language Processing. This year, EMNLP 2024 is being held in a hybrid format,
offering both virtual and in-person participation in beautiful Miami. Due to a record-breaking number of submissions, we've expanded the total number of accepted papers to accommodate more cutting-edge research from around the globe.
### [Conference Handbook](https://drive.google.com/file/d/1WPROgxjLAC96AJL7Ugy0tEnYm7dkrbHt/view?usp=sharing)

You are required to register for this event. **Please register [here](https://2024.emnlp.org/registration/).** The EMNLP 2024 event page on Underline will be open to public one week prior to the event.

Please register!

EMNLP 2024 will take place in Miami, Florida from Nov 12th to Nov 16th, 2024, at the Hyatt Regency Miami Hote and on Underline for remote participants.

This study investigates the potential of Large Language Models (LLMs) for reconstructing and constructing the physical world solely based on textual knowledge. It explores the impact of model performance on spatial understanding abilities. To enhance the comprehension of geometric and spatial relationships in the complex physical world, the study introduces a set of geometric conventions and develops a workflow based on multi-layer graphs and multi-agent system frameworks. It examines how LLMs achieve multi-step and multi-objective geometric inference in a spatial environment using multi-layer graphs under unified geometric conventions. Additionally, the study employs a genetic algorithm, inspired by large-scale model knowledge, to solve geometric constraint problems. In summary, this work innovatively explores the feasibility of using text-based LLMs as physical world builders and designs a workflow to enhance their capabilities.

Navigate Complex Physical Worlds via Geometrically Constrained LLM

Detecting biases in natural language understanding (NLU) for African American Vernacular English (AAVE) is crucial to developing inclusive natural language processing (NLP) systems. To address dialect-induced performance discrepancies, we introduce AAVENUE (AAVE Natural Language Understanding Evaluation), a benchmark for evaluating large language model (LLM) performance on NLU tasks in AAVE and Standard American English (SAE). AAVENUE builds upon and extends existing benchmarks like VALUE, replacing deterministic syntactic and morphological transformations with a more flexible methodology leveraging LLM-based translation with few-shot prompting, improving performance across our evaluation metrics when translating key tasks from the GLUE and SuperGLUE benchmarks. We compare AAVENUE and VALUE translations using five popular LLMs and a comprehensive set of metrics including fluency, BARTScore, quality, coherence, and understandability. Additionally, we recruit fluent AAVE speakers to validate our translations for authenticity. Our evaluations reveal that LLMs consistently perform better on SAE tasks than AAVE-translated versions, underscoring inherent biases and highlighting the need for more inclusive NLP models.

AAVENUE: Detecting LLM Biases on NLU Tasks in AAVE via a Novel Benchmark

As large language models (LLMs) gain traction in healthcare, concerns about their susceptibility to demographic biases are growing. We introduce DiversityMedQA, a novel benchmark designed to assess LLM responses to medical queries across diverse patient demographics, such as gender and ethnicity. By perturbing questions from the MedQA dataset, which comprises of medical board exam questions, we created a benchmark that captures the nuanced differences in medical diagnosis across varying patient profiles. To ensure that our perturbations did not alter the clinical outcomes, we implemented a filtering strategy to validate each perturbation, so that any performance discrepancies would be indicative of bias. Our findings reveal notable discrepancies in model performance when tested against these demographic variations. By releasing DiversityMedQA, we provide a resource for evaluating and mitigating demographic bias in LLM medical diagnoses.

DiversityMedQA: A Benchmark for Assessing Demographic Biases in Medical Diagnosis using Large Language Models

In this paper, we propose a novel application to improve industrial safety by generating preventive recommendations using LLMs. Using a dataset of 275 incidents representing 11 different incident types sampled from real-life OSHA incidents, we compare three different LLMs to evaluate the quality of preventive recommendations generated by them. We also show that LLMs are not a panacea for the preventive recommendation generation task. They have limitations and can produce responses that are incorrect or irrelevant. We found that about 65% of the output from Vicuna model was not acceptable at all at the basic readability and other sanity checks level. Mistral and Phi_3 are better than Vicuna, but not all of their recommendations are of similar quality. We find that for a given safety incident case, the generated recommendations can be categorized as specific, generic, or irrelevant. This helps us to better quantify and compare the performance of the models. This paper is among the initial and novel work for the preventive recommendation generation problem. We believe it will pave way for use of NLP to positively impact the industrial safety.

Improving Industrial Safety by Auto-Generating Case-specific Preventive Recommendations

Recently, work in NLP has shifted to few-shot (in-context) learning, with large language models (LLMs) performing well across a range of tasks. However, while fairness evaluations have become a standard for supervised methods, little is known about the fairness of LLMs as prediction systems. Further, common standard methods for fairness involve access to model weights or are applied during finetuning, which are not applicable in few-shot learning. Do LLMs exhibit prediction biases when used for standard NLP tasks?

In this work, we analyze the effect of shots, which directly affect the performance of models, on the fairness of LLMs as NLP classification systems. We consider how different shot selection strategies, both existing and new demographically sensitive methods, affect model fairness across three standard fairness datasets. We find that overall the performance of LLMs is not indicative of their fairness, and there is not a single method that fits all scenarios. In light of these facts, we discuss how future work can include LLM fairness in evaluations.

Selecting Shots for Demographic Fairness in Few-Shot Learning with Large Language Models

To address the challenges of Multimodal Fake News Detection (MFND), numerous Multimodal Small Language Models (MSLMs) have been developed. 
However, these models lack the breadth of knowledge, depth of language understanding, which results in unsatisfactory adaptability, generalization, and explainability performance.
Large Vision-Language Models (LVLMs) have shown significant performance in various tasks. Naturally, we hope to apply the common sense understanding and logical reasoning abilities of LVLMs to the task of MFND.
We found that LVLMs can generate reasonable analyses of the news from a specific perspective quite well.
However, when tasked with synthesizing these analyses to render a final judgment and explanations, their performance deteriorates significantly, failing to meet the accuracy standards set by existing detection models.
Based on these findings, we propose the Explainable Adaptive Rationales-Augmented Multimodal (EARAM) framework, which adaptively extracts useful rationales for news detection from the multi-perspective analyses of Retrieval-Augmented LVLMs through MSLMs.After making judgments based on these rationales, EARAM then assists LVLMs in generating more reliable explanations. Experiments demonstrate that our model not only achieves excellent results on widely used datasets but also significantly outperforms other models in terms of generalization and explainability.

From Predictions to Analyses: Explainable Rationales-Augmented Fake News Detection with Large Vision-Language Models

While various approaches have recently been studied for bias identification, little is known about how implicit language that does not explicitly convey a viewpoint affects bias amplification in large language models. To examine the severity of bias toward a view, we evaluated the performance of two downstream tasks where the implicit and explicit knowledge of social groups were used. First, we present a stress test evaluation by using a biased model in edge cases of excessive bias scenarios. Then, we evaluate how LLMs calibrate linguistically in response to both implicit and explicit opinions when they are aligned with conflicting viewpoints. 
Our findings reveal a discrepancy in LLM performance in identifying implicit and explicit opinions, with a general tendency of bias toward explicit opinions of opposing stances. Moreover, the bias-aligned models generate more cautious responses using uncertainty phrases compared to the unaligned (zero-shot) base models. The direct, incautious responses of the unaligned models suggest a need for further refinement of decisiveness by incorporating uncertainty markers to enhance their reliability, especially on socially nuanced topics with high subjectivity.

Covert Bias: The Severity of Social Views' Unalignment in Language Models Towards Implicit and Explicit Opinion

Technological advancements have enabled citizens to collectively share their opinions and report on election-related issues in real time. Systematically organizing (e.g., categorizing by attributes) and geotagging large amounts of crowdsourced information is crucial to ensuring that accurate and meaningful insights can be drawn from this data and used by policy makers to bring about positive change. However, these tasks typically require extensive manual efforts. In this paper we present Uchaguzi-2022, a dataset of 14k crowdsourced geotagged reports related to the 2022 Kenyan General Election. We use this dataset to investigate whether language models can assist in scalably categorizing and geotagging reports and show that they can achieve reasonable performance on these tasks.

Uchaguzi-2022: A Dataset of Citizen Reports on the 2022 Kenyan Election

Reference at the Heart of Natural Language Processing

The capabilities of AI in the realm of science span a wide spectrum, from the atomic level, where it solves partial differential equations for quantum systems, to the molecular level, predicting chemical or protein structures, and even extending to societal predictions like infectious disease outbreaks. Recent advancements in large language models (LLMs), exemplified by models like ChatGPT, have showcased significant prowess in tasks involving natural language, such as translating languages, constructing chatbots, and answering questions. When we consider scientific data, we notice a resemblance to natural language in terms of sequences – scientific literature and health records presented as text, bio-omics data arranged in sequences, or sensor data like brain signals. The question arises: Can we harness the potential of these recent LLMs to drive scientific progress? In this tutorial, we will explore the application of large language models to three crucial categories of scientific data: 1) textual data, 2) biomedical sequences, and 3) brain signals. Furthermore, we will delve into LLMs’ challenges in scientific research, including ensuring trustworthiness, achieving personalization, and adapting to multi-modal data representation.

Downloads

Next from EMNLP 2024

Navigate Complex Physical Worlds via Geometrically Constrained LLM

Similar lecture

Exploring Artificial Image Generation for Stance Detection

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2024

Navigate Complex Physical Worlds via Geometrically Constrained LLM

Similar lecture

Exploring Artificial Image Generation for Stance Detection

Downloads