Thailand

In this work, we investigate the controllability of large language models (LLMs) on scientific summarization tasks. We identify key stylistic and content coverage factors that characterize different types of summaries such as paper reviews, abstracts, and lay summaries. By controlling stylistic features, we find that non-fine-tuned LLMs outperform humans in the MuP review generation task, both in terms of similarity to reference summaries and human preferences. Also, we show that we can improve the controllability of LLMs with keyword-based classifier-free guidance (CFG) while achieving lexical overlap comparable to strong fine-tuned baselines on arXiv and PubMed. However, our results also indicate that LLMs cannot consistently generate long summaries with more than 8 sentences. Furthermore, these models exhibit limited capacity to produce highly abstractive lay summaries. Although LLMs demonstrate strong generic summarization competency, sophisticated content control without costly fine-tuning remains an open problem for domain-specific applications.

ACL 2024

Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?

llms

scientific

long documents

summarization

It is my great pleasure and honor to welcome you to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), held in San Diego, California, USA, July 2–7, 2026. ACL 2026 continues our fields 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.

It is exciting to see the many developments in the field reflected at our conference, such as the advancement of large language models (born out of our community) into many application directions. This is not without challenges, partly due to unsolved problems, and partly due to misuse of the technology. All this is reflected well at ACL 2026. The conference also reflects that the field is not only about advancing technology, but also the science of fundamentally understanding language and how it is use by many different speaker communities. 
[Full Message from General Chair Philipp Koehn](https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing) 
<html><button style="display: inline-flex; align-items: center; justify-content: center; white-space: nowrap; border-radius: 9999px; font-weight: bold; background: #7c3aed; color: white; font-family: 'Space Grotesk', sans-serif; height: 40px; font-size: 16px; padding: 0 20px; border: none; cursor: pointer" onclick="window.open('https://drive.google.com/file/d/1QiJFOmMjvDgsDo3i1XzlQnImxe3RU_Cy/view?usp=sharing')">Conference Handbook</button></html>

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 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://2026.aclweb.org/registration/) first.

Registration Required

ACL 2026

The 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) will take place in San Diego, California, from July 2 - 7, 2026.

poster

### 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.

Recent advancements in large language models have heavily relied on the large reward model from reinforcement learning from human feedback for fine-tuning. However, the use of a single reward model across various domains may not always be optimal, often requiring retraining from scratch when new domain data is introduced. To address these challenges, we explore the utilization of small language models operating in a domain-specific manner based on router mechanisms. Our three approaches are: 1) utilize mixture of experts to form a single reward model by modularizing an internal router and experts, 2) employing external router to select the appropriate reward model from multiple domain-specific models, and 3) the framework reduces parameter size by loading reward models and router adapters onto a single small language model using adapters. Experimental validation underscores the effectiveness of our approach, demonstrating performance comparable to baseline methods while also reducing the total parameter size.

Exploring Domain Robust Lightweight Reward Models based on Router Mechanism

Text embedding requires a highly efficient method for training domain-specific models on limited data, as general models trained on large corpora lack universal applicability in highly specific fields. Therefore, we have introduced VAEGPT-Sim, an innovative model for generating synonyms that combines a denoising variational autoencoder with a target-specific discriminator to generate synonymous sentences that closely resemble human language. Even when trained with completely unsupervised settings, it maintains a harmonious balance between semantic similarity and lexical diversity, as shown by a comprehensive evaluation metric system with the highest average scores compared to other generative models. When VAEGPT-Sim is utilized as a module for contrastive learning in text representation, it delivers state-of-the-art results in small-dataset training on STS benchmarks, surpassing ConSERT by 2.8 points. This approach optimizes the effectiveness of text representation despite a limited corpus, signifying an advancement in domain-specific embedding technology.

VAEGPT-Sim: Improving Sentence Representation with Limited Corpus Using Gradually-Denoising VAE

This paper addresses the critical challenge of assessing the representativeness of news thumbnail images, which often serve as the first visual engagement for readers when an article is disseminated on social media. We focus on whether a news image represents the actors discussed in the news text. To serve the challenge, we introduce NewsTT, a manually annotated dataset of 1000 news thumbnail images and text pairs. We found that the pretrained vision and language models, such as BLIP-2, struggle with this task. Since news subjects frequently involve named entities or proper nouns, the pretrained models could have a limited capability to match news actors' visual and textual appearances. We hypothesize that learning to contrast news text with its counterfactual, of which named entities are replaced, can enhance the cross-modal matching ability of vision and language models. We propose CFT-CLIP, a contrastive learning framework that updates vision and language bi-encoders according to the hypothesis. We found that our simple method can boost the performance for assessing news thumbnail representativeness, supporting our assumption. Code and data can be accessed at https://github.com/ssu-humane/news-images-acl24.

Assessing News Thumbnail Representativeness: Counterfactual text can enhance the cross-modal matching ability

Structured entailment tree can exhibit the reasoning chains from knowledge facts to predicted answers, which is important for constructing an explainable question answering system. Existing works mainly include directly generating the entire tree and stepwise generating the proof steps. The stepwise methods can exploit combinatoriality and generalize to longer steps, but they have large fact search spaces and error accumulation problems resulting in the generation of invalid steps. In this paper, inspired by the Dual Process Theory in cognitive science, we propose FRVA, a Fact-Retrieval and Verification Augmented bidirectional entailment tree generation method that contains two systems. Specifically, System 1 makes intuitive judgments through the fact retrieval module and filters irrelevant facts to reduce the search space. System 2 designs a deductive-abductive bidirectional reasoning module, and we construct cross-verification and multi-view contrastive learning to make the generated proof steps closer to the target hypothesis. We enhance the reliability of the stepwise proofs to mitigate error propagation. Experiment results on EntailmentBank show that FRVA outperforms previous models and achieves state-of-the-art performance in fact selection and structural correctness.

FRVA: Fact-Retrieval and Verification Augmented Entailment Tree Generation for Explainable Question Answering

Information extraction plays a critical role in natural language processing. When applying large language models (LLMs) to this domain, we discover an unexpected phenomenon: LLMs’ spurious associations. In tasks such as relation extraction, LLMs can accurately identify entity pairs, even if the given relation (label) is semantically unrelated to the pre-defined original one. To find these labels, we design two strategies in this study, including forward label extension and backward label validation. We also leverage the extended labels to improve model performance. Our comprehensive experiments show that spurious associations occur consistently in both Chinese and English datasets across various LLM sizes. Moreover, the use of extended labels significantly enhances LLM performance in information extraction tasks. Remarkably, there is a performance increase of 9.55\%, 11.42\%, and 21.27\% in F1 scores on the SciERC, ACE05, and DuEE datasets, respectively.

Unexpected Phenomenon: LLMs' Spurious Associations in Information Extraction

Zero-shot entity and relation classification models leverage available external information of unseen classes -- e.g., textual descriptions -- to annotate input text data. Thanks to the minimum data requirement, Zero-Shot Learning (ZSL) methods have high value in practice, especially in applications where labeled data is scarce. Even though recent research in ZSL has demonstrated significant results, our analysis reveals that those methods are sensitive to provided textual descriptions of entities (or relations). Even a minor modification of descriptions can lead to a change in the decision boundary between entity (or relation) classes. In this paper, we formally define the problem of identifying effective descriptions for zero shot inference. We propose a strategy for generating variations of an initial description, a heuristic for ranking them and an ensemble method capable of boosting the predictions of zero-shot models through description enhancement. Empirical results on four different entity and relation classification datasets show that our proposed method outperform existing approaches and achieve new SOTA results on these datasets under the ZSL settings. The source code of the proposed solutions and the evaluation framework are open-sourced.

Description Boosting for Zero-Shot Entity and Relation Classification

In everyday language use, speakers frequently utter and interpret sentences that are semantically underspecified, namely, whose content is insufficient to fully convey their message or interpret them univocally. For example, to interpret the underspecified sentence "Don't spend too much", which leaves implicit what (not) to spend, additional linguistic context or outside knowledge is needed. In this work, we propose a novel Dataset of semantically Underspecified Sentences grouped by Type (DUST) and use it to study whether pre-trained language models (LMs) correctly identify and interpret underspecified sentences. We find that newer LMs are reasonably able to identify underspecified sentences when explicitly prompted. However, interpreting them correctly is much harder for any LMs. Our experiments show that when interpreting underspecified sentences, LMs exhibit little uncertainty, contrary to what theoretical accounts of underspecification would predict. Overall, our study reveals limitations in current models' processing of sentence semantics and highlights the importance of using naturalistic data and communicative scenarios when evaluating LMs' language capabilities.

Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST!

With the popularity of large language models (LLMs) and their ability to handle longer input documents, there is a growing need for high-quality long document summarization datasets. Although many models already support 16k input, current lengths of summarization datasets are inadequate, and salient information is not evenly distributed. To bridge these gaps, we collect a new summarization dataset called SumSurvey, consisting of more than 18k scientific survey papers. With an average document length exceeding 12k and a quarter exceeding 16k, as well as the uniformity metric outperforming current mainstream long document summarization datasets, SumSurvey brings new challenges and expectations to both fine-tuned models and LLMs. The informativeness of summaries and the models supporting the evaluation of long document summarization warrant further attention. Automatic and human evaluation results on this abstractive dataset confirm this view. Our dataset and code are available at https://github.com/Oswald1997/SumSurvey.

SumSurvey: An Abstractive Dataset of Scientific Survey Papers for Long Document Summarization

The rapid increase in multimedia data has spurred advancements in Multimodal Summarization with Multimodal Output (MSMO), which aims to produce a multimodal summary that integrates both text and relevant images. The inherent heterogeneity of content within multimodal inputs and outputs presents a significant challenge to the execution of MSMO. Traditional approaches typically adopt a holistic perspective on coarse image-text data or individual visual objects, overlooking the essential connections between objects and the entities they represent. To integrate the fine-grained entity knowledge, we propose an Entity-Guided Multimodal Summarization model (EGMS). Our model, building on BART, utilizes dual multimodal encoders with shared weights to process text-image and entity-image information concurrently. A gating mechanism then combines visual data for enhanced textual summary generation, while image selection is refined through knowledge distillation from a pre-trained vision-language model. Extensive experiments on public MSMO dataset validate the superiority of the EGMS method, which also prove the necessity to incorporate entity information into MSMO problem.

Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization

In-context learning (ICL) has emerged as a powerful tool for enhancing large language models (LLMs) in addressing downstream tasks. In this paper, we explore the vital task of example selection in ICL by mimicking the human learning process. We propose a Chain-of-Quizzes (CoQ) framework inspired by educational theories such as Bruner's Spiral Learning and Mastery Learning theory. Specifically, our framework employs the LLMs to answer the quiz (question in the example) to sift `good' examples, combines these examples iteratively with the increasing complexity, and utilizes a final exam to gauge the combined example chains. Our extensive experiments on diverse reasoning datasets show the proposed approach outperforms baseline models. These findings underscore the framework's potential for future research.

Downloads

Next from ACL 2024

Exploring Domain Robust Lightweight Reward Models based on Router Mechanism

Similar lecture

Understanding LLMs' summarization capabilities: an analysis of biomedical abstract and lay summary generation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.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 2024

Exploring Domain Robust Lightweight Reward Models based on Router Mechanism

Similar lecture

Understanding LLMs' summarization capabilities: an analysis of biomedical abstract and lay summary generation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads