Austria

This paper presents a new system for generating critical questions in debates, developed for the Critical Questions Generation shared task. Our two-stage approach, combining generation and classification, utilizes LLaMA 3.1 Instruct models (8B, 70B, 405B) with zero-/few-shot prompting. Evaluations on annotated debate data reveal several key insights: few-shot generation with 405B yielded relatively high-quality questions, achieving a maximum possible punctuation score of 73.5. The 70B model outperformed both smaller and larger variants on the classification part. The classifiers showed a strong bias toward labeling generated questions as Useful, despite limited validation. Further, our system, ranked 6th, outperformed baselines by 3%. These findings stress the effectiveness of large-sized models for question generation and medium-sized models for classification, and suggest the need for clearer task definitions within prompts to improve classification accuracy.

ACL 2025

TriLLaMa at CQs-Gen 2025: A Two-Stage LLM-Based System for Critical Question Generation

## 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.

workshop paper

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

In this paper, we present our submission to the MM-ArgFallacy2025 shared task, which aims to advance research in multimodal argument mining, focusing on logical fallacies in political debates. Our approach uses pretrained Transformer-based models and proposes several ways to leverage context. In the fallacy classification subtask, our models achieved macro F1-scores of 0.4444 (text), 0.3559 (audio), and 0.4403 (multimodal). Our multimodal model showed performance comparable to the text-only model, suggesting potential for improvements.

Leveraging context for multi-modal fallacy classification in political debates

We address the detection of emission reduction goals in corporate reports, an important task for monitoring companies' progress in addressing climate change. Specifically, we focus on the issue of integrating expert feedback in the form of labeled example passages into LLM-based pipelines, and compare the two strategies of (1) a dynamic selection of few-shot examples and (2) the automatic optimization of the prompt by the LLM itself. 
Our findings on a public dataset of 769 climate-related passages from real-world business reports indicate that automatic prompt optimization is the superior approach, while combining both methods provides only limited benefit. Qualitative results indicate that optimized prompts do indeed capture many intricacies of the targeted emission goal extraction task.

Integrating Expert Labels into LLM-based Emission Goal Detection: Example Selection vs Automatic Prompt Design

Large Language Models (LLMs) are increasingly used in applications that shape public discourse, yet little is known about
whether they reflect distinct opinions on global issues like climate change. This study compares climate change-related
responses from multiple LLMs with human opinions collected through the People's Climate Vote 2024 survey (UNDP -- United
Nations Development Programme and Oxford, 2024). We compare country and LLM''s answer probability distributions and apply Exploratory Factor Analysis (EFA) to identify latent opinion dimensions. Our findings reveal that while LLM responses
do not exhibit significant biases toward specific demographic groups, they encompass a wide range of opinions, sometimes
diverging markedly from the majority human perspective.

AI and Climate Change Discourse: What Opinions Do Large Language Models Present?

The European Union Deforestation Regulation (EUDR) requires companies to prove their products do not contribute to deforestation, creating a critical demand for precise, asset-level environmental impact data. Current databases lack the necessary detail, relying heavily on broad financial metrics and manual data collection, which limits regulatory compliance and accurate environmental modeling. This study presents an automated, end-to-end data extraction pipeline that uses LLMs to create, clean, and validate structured databases, specifically targeting sectors with a high risk of deforestation. The pipeline introduces Instructional, Role-Based, Zero-Shot Chain-of-Thought (IRZ-CoT) prompting to enhance data extraction accuracy and a Retrieval-Augmented Validation (RAV) process that integrates real-time web searches for improved data reliability. Applied to SEC EDGAR filings in the Mining, Oil \& Gas, and Utilities sectors, the pipeline demonstrates significant improvements over traditional zero-shot prompting approaches, particularly in extraction accuracy and validation coverage. This work advances NLP-driven automation for regulatory compliance, CSR (Corporate Social Responsibility), and ESG, with broad sectoral applicability.

An Automated LLM-based Pipeline for Asset-Level Database Creation to Assess Deforestation Impact

Reforestation and revegetation projects can help mitigate climate change because plant growth removes CO$_2$ from the air. However, the use of non-native species and monocultures in these projects may negatively affect biodiversity. Here, we describe a data pipeline to extract information about species that are planted or managed in over 1,000 afforestation/reforestation/revegetation and improved forest management projects, based on detailed project documentation. The pipeline leverages a large-context LLM and results in a macro-averaged recall of 79\% and a macro-averaged precision of 89\% across all projects and species.

Scaling Species Diversity Analysis in Carbon Credit Projects with Large-Context LLMs

ClimateEval is a comprehensive benchmark designed to evaluate natural language processing models across a broad range of tasks related to climate change. ClimateEval aggregates existing datasets along with a newly developed news classification dataset, created specifically for this release. This results in a benchmark of 25 tasks based on 13 datasets, covering key aspects of climate discourse, including text classification, question answering, and information extraction. Our benchmark provides a standardized evaluation suite for systematically assessing the performance of large language models (LLMs) on these tasks. Additionally, we conduct an extensive evaluation of open-source LLMs (ranging from 2B to 70B parameters) in both zero-shot and few-shot settings, analyzing their strengths and limitations in the domain of climate change.

ClimateEval: A Comprehensive Benchmark for NLP Tasks Related to Climate Change

Misinformation about climate science is a serious challenge for our society. This paper introduces CPIQA (Climate Paper Image Question-Answering), a new question-answer dataset featuring 4,551 full-text open-source academic papers in the area of climate science with 54,612 GPT-4o generated question-answer pairs. CPIQA contains four question types (numeric, figure-based, non-figure-based, reasoning), each generated using three user roles (expert, non-expert, climate sceptic). CPIQA is multimodal, incorporating information from figures and graphs with GPT-4o descriptive annotations. We describe Context-RAG, a novel method for RAG prompt decomposition and augmentation involving extracting distinct contexts for the question. Evaluation results for Context-RAG on the benchmark SPIQA dataset outperforms the previous best state of the art model in two out of three test cases. For our CPIQA dataset, Context-RAG outperforms our standard RAG baseline on all five base LLMs we tested, showing our novel contextual decomposition method can generalize to any LLM architecture. Expert evaluation of our best performing model (GPT-4o with Context-RAG) by climate science experts highlights strengths in precision and provenance tracking, particularly for figure-based and reasoning questions.

CPIQA: Climate Paper Image Question Answering Dataset for Retrieval-Augmented Generation with Context-based Query Expansion

Large language models that use retrieval augmented generation have the potential to unlock valuable knowledge for researchers, policymakers, and the public by making long and technical climate-related documents more accessible. While this approach can help alleviate factual hallucinations by relying on retrieved passages as additional context, its effectiveness depends on whether the model's output remains faithful to these passages. To address this, we explore the automatic assessment of faithfulness of different models in this setting. We then focus on ClimateGPT, a large language model specialised in climate science, to examine which factors in its instruction fine-tuning impact the model's faithfulness. By excluding unfaithful subsets of the model's training data, we develop ClimateGPT Faithful+, which achieves an improvement in faithfulness from 30\% to 57\% in supported atomic claims according to our automatic metric.

Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate Questions

Research syntheses, such as systematic maps or evidence and gap maps, provide valuable overviews of the coverage of research in a particular field.
They serve as pointers for funders and researchers to identify important gaps in the literature where more research is needed but also to find relevant work for more in-depth systematic reviews or meta-analyses.
However, systematic maps become outdated quickly, sometimes even after they are released due to the time it takes to screen and code the available literature and long publication processes.
Furthermore, the write-up of the synthesis (in form of a peer-reviewed article) can only serve as a high-level summary---for detailed questions one would need full access to the underlying data.
To this end, we developed an interactive web-based platform to share annotated datasets.
For some datasets, where automated categorisation passes the necessary scientific quality standards, we also update the data as new research becomes available and thus make them `living'.

Interactive platform for the exploration of large-scale 'living' systematic maps

Accurately synthesizing climate evidence into concise statements is crucial for policy making and fostering public trust in climate science. Recent advancements in Large Language Models (LLMs), particularly the emergence of reasoning-optimized variants, which excel at mathematical and logical tasks, present a promising yet untested opportunity for scientific evidence synthesis. We evaluate state-of-the-art reasoning LLMs on two key tasks: (1) *contextual confidence classification*, assigning appropriate confidence levels to climate statements based on evidence, and (2) *factual summarization of climate evidence*, generating concise summaries evaluated for coherence, faithfulness, and similarity to expert-written versions. Using a novel dataset of 612 structured examples constructed from the Sixth Assessment Report (AR6) of the Intergovernmental Panel on Climate Change (IPCC), we find reasoning LLMs outperform general-purpose models in confidence classification by 8 percentage points in accuracy and macro-F1 scores. However, for summarization tasks, performance differences between model types are mixed. Our findings demonstrate that reasoning LLMs show promise as auxiliary tools for confidence assessment in climate evidence synthesis, while highlighting significant limitations in their direct application to climate evidence summarization. This work establishes a foundation for future research on the targeted integration of LLMs into scientific assessment workflows.

Content not yet available

Downloads

Next from ACL 2025

Leveraging context for multi-modal fallacy classification in political debates

Similar lecture

Benchmarking Critical Questions Generation: A Challenging Reasoning Task for Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Content not yet available

.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 ACL 2025

Leveraging context for multi-modal fallacy classification in political debates

Similar lecture

Benchmarking Critical Questions Generation: A Challenging Reasoning Task for Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads