Malta

Strategies such as chain-of-thought prompting improve the performance of large language models (LLMs) on complex reasoning tasks by decomposing input examples into intermediate steps. However, it remains unclear how to apply such methods to reason over long input documents, in which both the decomposition and the output of each intermediate step are non-trivial to obtain. In this work, we propose PEARL, a prompting framework to improve reasoning over long documents, which consists of three stages: action mining, plan formulation, and plan execution. More specifically, given a question about a long document, PEARL decomposes the question into a sequence of actions (e.g., SUMMARIZE, FIND_EVENT, FIND_RELATION) and then executes them over the document to obtain the answer. Each stage of PEARL is implemented via zero-shot or few-shot prompting of LLMs (in our work, GPT-4) with minimal human input. We evaluate PEARL on a challenging subset of the QuALITY dataset, which contains questions that require complex reasoning over long narrative texts. PEARL outperforms zero-shot and chain-of-thought prompting on this dataset, and ablation experiments show that each stage of PEARL is critical to its performance. Overall, PEARL is a first step towards leveraging LLMs to reason over long documents.

EACL 2024

PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents

long-document qa

prompting method

large language models

## 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.

poster

Welcome to the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Continuing its mission of expanding and involving the science community of all European countries, EACL has selected the Malta community for the 18th EACL. Considering the importance of physical interaction among researchers, the conference will be held at the Hotel Radisson Blu, St. Julians, in Malta, from 17 to 22 of March, 2024. The conference will also feature the possibility to participate virtually. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language. 
#### [Conference Handbook](https://drive.google.com/file/d/13Wn38q0yev6U3RTgnf4Tn5T9GuAuZ-xW/view?usp=sharing) *downloadable*

To access the EACL 2024 event page you need to register [**here**](https://acl.swoogo.com/EACL2024). 

Please register!

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

Techniques, Tactics and Procedures (TTP) mapping is an important and difficult task in the application of cyber threat intelligence (CTI) extraction for threat reports. TTPs are typically expressed in semantic forms within security knowledge bases like MITRE ATT&CK, serving as textual high-level descriptions for sophisticated attack patterns. Conversely, attacks in CTI threat reports are detailed in a combination of natural and technical language forms, presenting a significant challenge even for security experts to establish correlations or mappings with the corresponding TTPs.

Conventional learning approaches often target the TTP mapping problem in the classical multiclass/label classification setting. This setting hinders the learning capabilities of the model, due to the large number of classes (i.e., TTPs), the inevitable skewness of the label distribution and the complex hierarchical structure of the label space. In this work, we approach the problem in a different learning paradigm, such that the assignment of a text to a TTP label is essentially decided by the direct semantic similarity between the two, thus, reducing the complexity of competing solely over the large labeling space. In order that, we propose a neural matching architecture that incorporates a sampling based learn-to-compare mechanism, facilitating the learning process of the matching model despite constrained resources.

Noise Contrastive Estimation-based Matching Framework for Low-resource Security Attack Pattern Recognition

Tailoring outputs from large language models, like ChatGPT, to implicit user preferences remains a challenge despite their impressive generative capabilities. In this paper, we propose a tri-agent generation pipeline comprising a generator, an instructor, and an editor to enhance output personalization. The generator produces an initial output, the instructor automatically generates editing instructions based on user preferences, and the editor refines the output to align with those preferences. The inference-only large language model (ChatGPT) serves as both the generator and editor, with a smaller model acting as the instructor to guide output generation. We train the instructor using editor-steered reinforcement learning, leveraging feedback from a large-scale editor model to optimize instruction generation. Experimental results on two abstractive summarization datasets demonstrate the effectiveness of our approach in generating outputs that better meet user expectations.

Personalized Abstractive Summarization by Tri-agent Generation Pipeline

Abstractive summarization models often generate factually inconsistent content particularly when the parametric knowledge of the model conflicts with the knowledge in the input document. In this paper, we analyze the robustness of fine-tuning based summarization models to the knowledge conflict, which we call factual adaptiveness. We utilize pre-trained language models to construct evaluation sets and find that factual adaptiveness is not strongly correlated with factual consistency on original datasets. Furthermore, we introduce a controllable counterfactual data augmentation method where the degree of knowledge conflict within the augmented data can be adjustable. Our experimental results on two pre-trained language models (PEGASUS and BART) and two fine-tuning datasets (XSum and CNN/DailyMail) demonstrate that our method enhances factual adaptiveness while achieving factual consistency on original datasets on par with the contrastive learning baseline.

Entity-level Factual Adaptiveness of Fine-tuning based Abstractive Summarization Models

Controlled text generation (CTG) seeks to guide large language model (LLM) output, that statistical language generation would conform to desired criteria. The current study presents a novel CTG algorithm that enforces adherence toward specific rhetorical relations in an LLM sentence-completion context by a parser-driven decoding scheme that requires no model fine-tuning. The method is validated both with automatic and human evaluation.

Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method

Deriving meaningful sentence embeddings is crucial in capturing the semantic relationship between texts. Recent advances in building sentence embedding models have centered on replacing traditional human-generated text datasets with those generated by LLMs. However, the properties of these widely used LLM-generated texts remain largely unexplored. Here, we evaluate the quality of the LLM-generated texts from four perspectives (Positive Text Repetition, Length Difference Penalty, Positive Score Compactness, and Negative Text Implausibility) and find that there exists an inherent difference between human and LLM-generated datasets. To further enhance sentence embeddings using both human and LLM-generated datasets, we propose a novel loss function that incorporates Positive-Negative sample Augmentation (PNA) within the contrastive learning objective. Our results demonstrate that PNA effectively mitigates the sentence anisotropy problem in Wikipedia corpus (-7% compared to CLHAIF) and simultaneously improves the Spearman's correlation in standard Semantic Textual Similarity (STS) tasks (+1.47% compared to CLHAIF).

Capturing the Relationship Between Sentence Triplets for LLM and Human-Generated Texts to Enhance Sentence Embeddings

Code-mixing, the blending of multiple languages within a single conversation, introduces a distinctive challenge, particularly in the context of response generation. Capturing the intricacies of code-mixing proves to be a formidable task, given the wide-ranging variations influenced by individual speaking styles and cultural backgrounds. In this study, we explore response generation within code-mixed conversations. We introduce a novel approach centered on harnessing the Big Five personality traits acquired in an unsupervised manner from the conversations to bolster the performance of response generation. These inferred personality attributes are seamlessly woven into the fabric of the dialogue context, using a novel fusion mechanism, \model. It uses an effective two-step attention formulation to fuse the dialogue and personality information. This fusion not only enhances the contextual relevance of generated responses but also elevates the overall performance of the model. Our experimental results, grounded in a dataset comprising of multi-party Hindi-English code-mix conversations, highlight the substantial advantages offered by personality-infused models over their conventional counterparts. This is evident in the increase observed in ROUGE and BLUE scores for the response generation task when the identified personality is seamlessly integrated into the dialogue context. Qualitative assessment for personality identification and response generation aligns well with our quantitative results.

Harmonizing Code-mixed Conversations: Personality-assisted Code-mixed Response Generation in Dialogues

Neural abstractive summarization models make summaries in an end-to-end manner, and little is known about how the source information is actually converted into summaries. In this paper, we define input sentences that contain essential information in the generated summary as source sentences and study how abstractive summaries are made by analyzing the source sentences. To this end, we annotate source sentences for reference summaries and system summaries generated by PEGASUS on document-summary pairs sampled from the CNN/DailyMail and XSum datasets. We also formulate automatic source sentence detection and compare multiple methods to establish a strong baseline for the task. Experimental results show that the perplexity-based method performs well in highly abstractive settings, while similarity-based methods perform robustly in relatively extractive settings.

Source Identification in Abstractive Summarization

Learning multilingual sentence embeddings is a fundamental task in natural language processing. Recent trends in learning both monolingual and multilingual sentence embeddings are mainly based on contrastive learning (CL) among an anchor, one positive, and multiple negative instances. In this work, we argue that leveraging multiple positives should be considered for multilingual sentence embeddings because (1) positives in a diverse set of languages can benefit cross-lingual learning, and (2) transitive similarity across multiple positives can provide reliable structural information for learning.
In order to investigate the impact of multiple positives in CL, we propose a novel approach, named MPCL, to effectively utilize multiple positive instances to improve the learning of multilingual sentence embeddings. Experimental results on various backbone models and downstream tasks demonstrate that MPCL leads to better retrieval, semantic similarity, and classification performance compared to conventional CL. We also observe that in unseen languages, sentence embedding models trained on multiple positives show better cross-lingual transfer performance than models trained on a single positive instance.

Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding

A stereotype is a generalized perception of a specific group of humans. It is often potentially encoded in human language, which is more common in texts on social issues. Previous works simply define a sentence as stereotypical and anti-stereotypical. However, the stereotype of a sentence may require fine-grained quantification. In this paper, to fill this gap, we quantify stereotypes in language by annotating a dataset. We use the pre-trained language models (PLMs) to learn this dataset to predict stereotypes of sentences. Then, we discuss stereotypes about common social issues such as hate speech, sexism, sentiments, and disadvantaged and advantaged groups. We demonstrate the connections and differences between stereotypes and common social issues, and all four studies validate the general findings of the current studies. In addition, our work suggests that fine-grained stereotype scores are a highly relevant and competitive dimension for research on social issues. The models and datasets used in this paper are available at https://anonymous.4open.science/r/quantifying_stereotypes_in_language.

Quantifying Stereotypes in Language

Frames of Communication (FoCs) are ubiquitous in social media discourse. They define what counts as a problem, diagnose what is causing the problem, elicit moral judgments and imply remedies for resolving the problem. Most research on automatic frame detection involved the recognition of the problems addressed by frames, but did not consider the articulation of frames. Articulating an FoC involves reasoning with salient problems, their cause and eventual solution. In this paper we present a method for Discovering and Articulating FoCs (DA-FoC) that relies on a combination of Chain-of-Thought prompting of large language models (LLMs) with In-Context Active Curriculum Learning. Very promising evaluation results indicate that 86.72% of the FoCs encoded by communication experts on the same reference dataset were also uncovered by DA-FoC. Moreover, DA-FoC uncovered many new FoCs, which escaped the experts. Interestingly, 55.1% of the known FoCs were judged as being better articulated than the human-written ones, while 93.8% of the new FoCs were judged as having sound rationale and being clearly articulated.

Downloads

Next from EACL 2024

Noise Contrastive Estimation-based Matching Framework for Low-resource Security Attack Pattern Recognition

Similar lecture

Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset