Austria

Current exploration on creative generation focuses mainly on short stories, poetry, and scripts. With the expansion of Large Language Models (LLMs) context windows, &quot;novel&quot; avenues emerge. This study aims to extend the boundaries of Natural Language Generation (NLG) evaluation by exploring LLMs&#39; capabilities in more challenging long-form fiction. We propose a new multi-level evaluation framework that incorporates ten metrics across the Macro, Meso, and Micro levels. An annotated fiction dataset, sourced from human authors, LLMs, and human-AI collaborations in both English and Chinese is then constructed. Human evaluation reveals notable disparities between LLM-generated and human-authored fictions, particularly the “high-starting, low-ending” pattern in LLM outputs. We further probe ten high-performing LLMs through different prompt templates, achieving moderate correlations by strategically utilizing diverse LLMs tailored to different levels, as an initial step towards better automatic fiction evaluation. Finally, we offer a fine-grained analysis of LLMs capabilities through six issues, providing promising insights for future advancements.

ACL 2025

Towards A “Novel” Benchmark: Evaluating Literary Fiction with Large Language Models

generation

evaluation

## 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

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.

Current exploration on creative generation focuses mainly on short stories, poetry, and scripts. With the expansion of Large Language Models (LLMs) context windows, "novel" avenues emerge. This study aims to extend the boundaries of Natural Language Generation (NLG) evaluation by exploring LLMs' capabilities in more challenging long-form fiction. We propose a new multi-level evaluation framework that incorporates ten metrics across the Macro, Meso, and Micro levels. An annotated fiction dataset, sourced from human authors, LLMs, and human-AI collaborations in both English and Chinese is then constructed. Human evaluation reveals notable disparities between LLM-generated and human-authored fictions, particularly the “high-starting, low-ending” pattern in LLM outputs. We further probe ten high-performing LLMs through different prompt templates, achieving moderate correlations by strategically utilizing diverse LLMs tailored to different levels, as an initial step towards better automatic fiction evaluation. Finally, we offer a fine-grained analysis of LLMs capabilities through six issues, providing promising insights for future advancements.

poster

### 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)

Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Current approaches either assemble specialized expert models or directly generate page-level content autoregressively, facing integration overhead, efficiency bottlenecks, and layout structure degradation despite their decent performance. To address these limitations, we present Dolphin ( Document Image Parsing via Heterogeneous Anchor Prompting), a novel multimodal document image parsing model following an analyze-then-parse paradigm. In the first stage, Dolphin generates a sequence of layout elements in reading order. These heterogeneous elements, serving as anchors and coupled with task-specific prompts, are fed back to Dolphin for parallel content parsing in the second stage. To train Dolphin, we construct a large-scale dataset of over 30 million samples, covering multi-granularity parsing tasks. Through comprehensive evaluations on both prevalent benchmarks and self-constructed ones, Dolphin achieves state-of-the-art performance across diverse page-level and element-level settings, while ensuring superior efficiency through its lightweight architecture and parallel parsing mechanism. The code and pre-trained models are publicly available at https://github.com/ByteDance/Dolphin

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

Augmenting large language models (LLMs) with external context significantly improves their performance in natural language processing (NLP) tasks. However, LLMs struggle to answer queries reliably when the provided context lacks information, often resorting to ungrounded speculation or internal knowledge. Groundedness – generating responses strictly supported by the context – is essential for ensuring factual consistency and trustworthiness. This study focuses on detecting whether a given query is grounded in a document provided in context before the costly answer generation by LLMs. Such a detection mechanism can significantly reduce both inference time and resource consumption. We show that lightweight, task-specific encoder models such as RoBERTa and NomicBERT, fine-tuned on curated datasets, can achieve accuracy comparable to state-of-the-art LLMs, such as Llama3 8B and GPT4o, in groundedness detection while reducing inference latency by orders of magnitude.

Small Encoders Can Rival Large Decoders in Detecting Groundedness

With the growing adoption of Retrieval-Augmented Generation (RAG) in document processing, robust text recognition has become increasingly critical for knowledge extraction. While OCR (Optical Character Recognition) for English and other languages benefits from large datasets and well-established benchmarks, Arabic OCR faces unique challenges due to its cursive script, right-to-left text flow, and complex typographic and calligraphic features. We present KITAB-Bench, a comprehensive Arabic OCR benchmark that fills the gaps in current evaluation systems. Our benchmark comprises 8,809 samples across 9 major domains and 36 sub-domains, encompassing diverse document types including handwritten text, structured tables, and specialized coverage of 21 chart types for business intelligence. Our findings show that modern vision-language models (such as GPT-4, Gemini, and Qwen) outperform traditional OCR approached (like EasyOCR, PaddleOCR, and Surya) by an average of 60% in Character Error Rate (CER). Furthermore, we highlight significant limitations of current Arabic OCR models, particularly in PDF-to-Markdown conversion, where the best model Gemini-2.0-Flash achieves only 65% accuracy. This underscores the challenges in accurately recognizing Arabic text, including issues with complex fonts, numeral recognition errors, word elongation, and table structure detection. This work establishes a rigorous evaluation framework that can drive improvements in Arabic document analysis methods and bridge the performance gap with English OCR technologies.

KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

The field of machine translation has achieved significant advancements, yet domain-specific terminology translation, particularly in AI, remains challenging. This work introduces GIST, a large-scale multilingual AI terminology dataset containing 5K terms extracted from top AI conference papers spanning 2000 to 2023. The terms were translated into Arabic, Chinese, French, Japanese, and Russian using a hybrid framework that combines LLMs for extraction with human expertise for translation. The dataset's quality was benchmarked against existing resources, demonstrating superior translation accuracy through crowdsourced evaluation. GIST was integrated into translation workflows using post-translation refinement methods that required no retraining, where LLM prompting consistently improved BLEU and COMET scores. A web demonstration on the ACL Anthology platform highlights its practical application, showcasing improved accessibility for non-English speakers. We address a critical gap in AI terminology resources and fosters global inclusivity and collaboration in AI research.

Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)

Speculative Decoding has gained popularity as an effective technique for accelerating the auto-regressive inference process of Large Language Models. However, Speculative Decoding entirely relies on the availability of efficient draft models, which are often lacking for many existing language models due to a stringent constraint of vocabulary compatibility. In this work we introduce FastDraft, a novel and efficient approach for pre-training and aligning a draft model to any large language model by incorporating efficient pre-training, followed by fine-tuning over synthetic datasets generated by the target model. We demonstrate FastDraft by training two highly parameter efficient drafts for the popular Phi-3-mini and Llama-3.1-8B models. Using FastDraft, we were able to produce a draft with approximately 10 billion tokens on a single server with 8 Intel Gaudi 2 accelerators in under 24 hours. Our results show that the draft model achieves impressive results in key metrics of acceptance rate, block efficiency and up to 3x memory bound speed up when evaluated on code completion and up to 2x in summarization, text completion and instruction tasks. We validate our theoretical findings through benchmarking on the latest Intel Core Ultra, achieving a wall-clock time speedup of up to 2x, indicating a significant reduction in runtime. Due to its high quality, FastDraft unlocks large language models inference on AI-PC and other edge-devices.

FastDraft: How to Train Your Draft

Humor is prevalent in online communications and it often relies on more than one modality (e.g., cartoons and memes).
Interpreting humor in multimodal settings requires drawing on diverse types of knowledge, including metaphorical, sociocultural, and commonsense knowledge. However, identifying the most useful knowledge remains an open question. We introduce BottleHumor, a method inspired by the information bottleneck principle that elicits relevant world knowledge from vision and language models which is iteratively refined for generating an explanation of the humor in an unsupervised manner. Our experiments on three datasets confirm the advantage of our method over a range of baselines. Our method can further be adapted in the future for additional tasks that can benefit from eliciting and conditioning on relevant world knowledge and open new research avenues in this direction.

BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle

Slice discovery refers to identifying systematic biases in the mistakes of pre-trained vision models. Current slice discovery methods in computer vision rely on converting input images into sets of attributes and then testing hypotheses about configurations of these pre-computed attributes associated with elevated error patterns. However, such methods face several limitations: 1) they are restricted by the predefined attribute bank; 2) they lack the common sense reasoning and domain-specific knowledge often required for specialized fields e.g., radiology; 3) at best, they can only identify biases in image attributes while overlooking those introduced during preprocessing or data preparation. We hypothesize that bias-inducing variables leave traces in the form of language (e.g., logs), which can be captured as unstructured text. Thus, we introduce ladder, which leverages the reasoning capabilities and latent domain knowledge of Large Language Models (LLMs) to generate hypotheses about these mistakes. Specifically, we project the internal activations of a pre-trained model into text using a retrieval approach and prompt the LLM to propose potential bias hypotheses. To detect biases from preprocessing pipelines, we convert the preprocessing data into text and prompt the LLM. Finally, ladder generates pseudo-labels for each identified bias, thereby mitigating all biases without requiring expensive attribute annotations. Rigorous evaluations on 3 natural and 3 medical imaging datasets, 200+ classifiers, and 4 LLMs with varied architectures and pretraining strategies - demonstrate that\ladder consistently outperforms current methods. Code is available: \url{https://github.com/annonymous-vision/ACL}.

LADDER: Language-Driven Slice Discovery and Error Rectification in Vision Classifiers

Large Language Models (LLMs) excel at text summarization, a task that requires models to select content based on its importance. However, the exact notion of salience that LLMs have internalized remains unclear. To bridge this gap, we introduce an explainable framework to systematically derive and investigate information salience in LLMs through their summarization behavior. Using length-controlled summarization as a behavioral probe into the content selection process, and tracing the answerability of Questions Under Discussion throughout, we derive a proxy for how models prioritize information. Our experiments on 13 models across four datasets reveal that LLMs have a nuanced, hierarchical notion of salience, generally consistent across model families and sizes. While models show highly consistent behavior and hence salience patterns, this notion of salience cannot be accessed through introspection, and only weakly correlates with human perceptions of information salience.

Behavioral Analysis of Information Salience in Large Language Models

Multimodal Large Language Models (MLLMs) have shown strong performance in document image tasks, especially Optical Character Recognition (OCR). However, they struggle with Document Image Machine Translation (DIMT), which requires handling both cross-modal and cross-lingual challenges. Previous efforts to enhance DIMT capability through Supervised Fine-Tuning (SFT) on the DIMT dataset often result in the forgetting of the model's existing monolingual abilities, such as OCR. To address these challenges, we introduce a novel fine-tuning paradigm, named Synchronously Self-Reviewing (SSR) its OCR proficiency, inspired by the concept "Bilingual Cognitive Advantage". Specifically, SSR prompts the model to generate OCR text before producing translation text, which allows the model to leverage its strong monolingual OCR ability while learning to translate text across languages. Comprehensive experiments demonstrate the proposed SSR learning helps mitigate catastrophic forgetting, improving the generalization ability of MLLMs on both OCR and DIMT tasks. The code will be released upon acceptance.

Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency

In recent years, large language models (LLMs) have had great success in tasks such as casual conversation, contributing to significant advancements in domains like virtual assistance. However, they often generate responses that are not aligned with human values (e.g., ethical standards, safety), leading to potentially unsafe or inappropriate outputs. While several techniques have been proposed to address this problem, they come with a cost, requiring computationally expensive training or dramatically increasing the inference time. In this paper, we present DIESEL, a lightweight inference-guidance technique that can be seamlessly integrated into any autoregressive LLM to semantically filter undesired concepts from the response. DIESEL can function either as a standalone safeguard or as an additional layer of defense, enhancing response safety by reranking the LLM's proposed tokens based on their similarity to predefined negative concepts in the latent space. Our evaluation demonstrates DIESEL's effectiveness on state-of-the-art conversational models, even in adversarial jailbreaking scenarios that challenge response safety. We also highlight DIESEL's generalization capabilities, showing that it can be used in use cases other than safety, providing general-purpose response filtering.

Downloads

Next from ACL 2025

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

Similar lecture

Leveraging Large Language Models for NLG Evaluation: Advances and Challenges