China

Multimodal multihop question answering (MMQA) requires reasoning over images and text from multiple sources, an essential task for many real-world applications. Despite advances in visual question answering, this multihop setting remains underexplored due to a lack of quality datasets. Existing methods focus on single-hop, single-modality, or short texts, limiting real-world applications like interpreting educational documents with long, multimodal content. To fill this gap, we introduce FM2DS, the first framework for creating a high-quality dataset for MMQA. Our approach consists of a 5-stage pipeline that involves acquiring relevant multimodal documents from Wikipedia, synthetically generating high-level questions and answers, and validating them through rigorous criteria to ensure data quality. We evaluate our methodology by training models on our synthesized dataset and testing on two benchmarks: MultimodalQA and WebQA. Our results demonstrate that, with an equal sample size, models trained on our synthesized data outperform those trained on human-collected data by 1.9 in exact match (EM) score on average. Additionally, we introduce M2QA-Bench with 1k samples, the first benchmark for MMQA on long documents, generated using FM2DS and refined by human annotators.

EMNLP 2025

FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering

multihop

data synthesis

multimodal

question answering

knowledge distillation

### 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**. 

ACL 2025

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

poster

## 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*

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

Large language models (LLMs) are increasingly used to predict human emotions, but previous studies show that these models reproduce gendered emotion stereotypes. Emotion stereotypes are also tightly tied to race and skin tone (consider for example the trope of the angry black woman), but previous work has thus far overlooked this dimension. In this paper, we address this gap by introducing the first large-scale multimodal study of racial, gender, and skin-tone bias in emotion attribution, revealing how modality (text, images) and their combination shape emotion stereotypes in Multimodal LLMs (MLLMs). We evaluate four open-source MLLMs using 2.1K emotion-related events paired with 400 neutral face images across three different prompt strategies. Our findings reveal varying biases in MLLMs representations of different racial groups: models reproduce racial stereotypes across modalities, with textual cues being particularly noticeable. Models also reproduce colourist trends, with darker skin tones showing more skew. Our research highlights the need for future rigorous evaluation and mitigation strategies that account for race, colorism, and gender in MLLMs.

Seeing Race, Feeling Bias: Emotion Stereotyping in Multimodal Language Models

Pun generation seeks to creatively modify linguistic elements in text to produce humour or evoke double meanings. It also aims to preserve coherence and contextual appropriateness, making it useful in creative writing and entertainment across various media and contexts. This field has been widely studied in computational linguistics, while there are currently no surveys that specifically focus on pun generation. To bridge this gap, this paper provides a comprehensive review of pun generation datasets and methods across different stages, including traditional approaches, deep learning techniques, and pre-trained language models. Additionally, we summarise both automated and human evaluation metrics used to assess the quality of pun generation. Finally, we discuss the research challenges and propose promising directions for future work.

A Survey of Pun Generation: Datasets, Evaluations and Methodologies

CLIP’s success has demonstrated that prompt tuning can achieve robust cross-modal semantic alignment for tasks ranging from open-domain recognition to fine-grained classification. However, redundant or weakly relevant feature components introduce noise and incur unnecessary computational costs. In this work, we propose Spotlighter, a lightweight token-selection framework that simultaneously enhances accuracy and efficiency in prompt tuning. Spotlighter evaluates each visual token’s activation from both sample-wise and semantic-wise perspectives and retains only the top-scoring tokens for downstream prediction. A class-specific semantic memory bank of learned prototypes refines this selection, ensuring semantic representativeness and compensating for discarded features. To further prioritize informative signals, we introduce a two-level ranking mechanism that dynamically weights token–prototype interactions. Across 11 few-shot benchmarks, Spotlighter outperforms CLIP by up to 11.19% in harmonic mean accuracy and achieves up to 0.8K additional FPS, with only 21 extra parameters. These results establish Spotlighter as an effective and scalable baseline for prompt tuning.

Spotlighter: Revisiting Prompt Tuning from a Representative Mining View

Parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), offer an efficient way to adapt large language models with reduced computational costs. However, their performance is limited by the small number of trainable parameters. Recent work combines LoRA with the Mixture-of-Experts (MoE), i.e., LoRA-MoE, to enhance capacity, but two limitations remain in hindering the full exploitation of its potential: 1) the influence of downstream tasks when assigning expert numbers, and 2) the uniform rank assignment across all LoRA experts, which restricts representational diversity. To mitigate these gaps, we propose GuiLoMo, a fine-grained layer-wise expert numbers and ranks allocation strategy with GuidedSelection Vectors (GSVs). GSVs are learned via a prior bilevel optimization process to capture both model- and task-specific needs, and are then used to allocate optimal expert numbers and ranks. Experiments on three backbone models across diverse benchmarks show that GuiLoMo consistently achieves superior or comparable performance to all baselines. Further analysis offers key insights into how expert numbers and ranks vary across layers and tasks, highlighting the benefits of adaptive expert configuration. Our code is available at \url{https://anonymous.4open.science/r/GuiLoMo-034}.

GuiLoMo: Allocating Experts and Ranks for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors

Fine-tuning large language models (LLMs) for recommendation in a generative manner has delivered promising results, but encounters significant inference overhead due to autoregressive decoding in the language space. This work explores bypassing language-space decoding by directly matching candidate items with the LLM's internal thought representations in the latent space, eliminating the time-consuming autoregressive process to reduce computational costs. Towards this, we introduce Light Latent-space Decoding (L2D), an effective and efficient latent-space decoding method. L2D represents user-preferred items by using the hidden states of test sequences reflecting the LLM’s internal thought, and obtains candidate item representations from the hidden states of training sequences labeled with the corresponding candidate items. It then matches the two types of representations to decode items, achieving latent-space decoding. In this way, it enables efficient decoding without altering the LLM's generative tuning paradigm, thereby preserving performance. Extensive empirical results demonstrate that L2D is more than 10x faster than language-space decoding while maintaining or enhancing performance.

Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation

Compositional generalization is one of the important abilities that large language models (LLMs) need to have for semantic parsing. Previous research typically relies on dataset-specific designs or a large number of samples in demonstrations to improve the compositional generalization of LLMs on semantic parsing. We revisit this issue and find that when the number of samples in a demonstration is limited to a theoretical lower bound for achieving compositional generalization (minimum-coverage), current advanced LLMs cannot arbitrarily achieve good compositional generalization generically on different semantic parsing datasets without dataset-specific designs. To solve this problem, we propose Multi-level Component Composition (MC^2), a minimum-coverage and dataset-agnostic framework based on input primitives, which aims to generically help LLMs achieve compositional generalization by selecting and organizing samples from multiple compositional levels that satisfy the primitive coverage. Experiments and analysis show that MC^2 can effectively improve the compositional generalization of LLMs on different semantic parsing datasets in the minimum-coverage setting.

MC^2: A Minimum-Coverage and Dataset-Agnostic Framework for Compositional Generalization of LLMs on Semantic Parsing

We introduce GeoDANO, a geometric vision-language model (VLM) with a domain-agnostic vision encoder, for solving plane geometry problems. Although VLMs have been employed for solving geometry problems, their ability to recognize geometric features remains insufficiently analyzed. To address this gap, we propose a benchmark that evaluates the recognition of visual geometric features, including primitives such as dots and lines, and relations such as orthogonality. Our preliminary study shows that vision encoders often used in general-purpose VLMs, e.g., OpenCLIP, fail to detect these features and struggle to generalize across domains. To overcome the limitation, we develop GeoCLIP, a CLIP-based model trained on synthetic geometric diagram–caption pairs. Benchmark results show that GeoCLIP outperforms existing vision encoders in recognizing geometric features. We then propose our VLM, GeoDANO, which augments GeoCLIP with a domain adaptation strategy for unseen diagram styles. GeoDANO outperforms specialized methods for plane geometry problems and GPT-4o on MathVerse.

GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder

Event extraction (EE) is a fundamental task in natural language processing (NLP) that involves identifying and extracting event information from unstructured text. Effective EE in real-world scenarios requires two key steps: selecting appropriate schemas from hundreds of candidates and executing the extraction process. Existing research exhibits two critical gaps: (1) the rigid schema fixation in existing pipeline systems, and (2) the absence of benchmarks for evaluating joint schema matching and extraction. Although large language models (LLMs) offer potential solutions, their schema hallucination tendencies and context window limitations pose challenges for practical deployment. In response, we propose textbfAdaptive textbfSchema-aware textbfEvent textbfExtraction (textbfASEE), a novel paradigm combining schema paraphrasing with schema retrieval-augmented generation. ASEE adeptly retrieves paraphrased schemas and accurately generates targeted structures. To facilitate rigorous evaluation, we construct the textbfMulti-textbfDimensional textbfSchema-aware textbfEvent textbfExtraction (textbfMD-SEE) benchmark, which systematically consolidates 12 datasets across diverse domains, complexity levels, and language settings. Extensive evaluations on MD-SEE show that our proposed ASEE demonstrates strong adaptability across various scenarios, significantly improving the accuracy of event extraction. Our codes and datasets are available at https://anonymous.4open.science/r/ASEE-67BB

Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation

Event argument extraction aims to identify event arguments and classify their roles within events, whereas relation extraction classifies semantic relationships between entities. Existing methods struggle to leverage semantic interactions effectively. To address this issue, we propose REAR, a reinforced optimization framework. REAR first initializes a Large Language Model (LLM) with supervised reasoning explanations. Subsequently, it enhances the LLM by dynamically exploring reasoning trajectories via reinforcement learning. Experimental results show that REAR yields substantial improvements over previous decoder-only LLM methods, achieving performance gains of at least 0.9% and 2.2% in F1-score on the ACE-E and ACE-E benchmark datasets, respectively. All code will be made publicly available.

REAR: Reinforced Reasoning Optimization for Event Argument Extraction with Relation-Aware Support

Large language models (LLMs) commonly risk copyright infringement by reproducing protected content verbatim or with insufficient transformative modifications, posing significant ethical, legal, and practical concerns. Current inference-time safeguards predominantly rely on restrictive refusal-based filters, often compromising the practical utility of these models. To address this, we collaborated closely with intellectual property experts to develop FUA-LLM (Fair Use Aligned Language Models), a legally-grounded framework explicitly designed to align LLM outputs with fair-use doctrine. Central to our method is FairUseDB, a carefully constructed dataset containing 18,000 expert-validated examples covering nine realistic infringement scenarios. Leveraging this dataset, we apply Direct Preference Optimization (DPO) to fine-tune open-source LLMs, encouraging them to produce legally compliant and practically useful alternatives rather than resorting to blunt refusal. Recognizing the shortcomings of traditional evaluation metrics, we propose new measures: Weighted Penalty Utility and Compliance Aware Harmonic Mean (CAH) to balance infringement risk against response utility. Extensive quantitative experiments coupled with expert evaluations confirm that FUA-LLM substantially reduces problematic outputs (up to 20%) compared to state-of-the-art approaches, while preserving real-world usability.

Downloads

Next from EMNLP 2025

Seeing Race, Feeling Bias: Emotion Stereotyping in Multimodal Language Models

Similar lecture

MMInA: Benchmarking Multihop Multimodal Internet Agents