Mexico

We present an effective recipe to train strong long-context LLMs that are capable of utilizing massive context windows of up to 32,000 tokens. Our models are built through continual pretraining from Llama 2 checkpoints with longer text sequences and on a dataset where long texts are upsampled. We perform extensive evaluation using language modeling, synthetic context probing tasks, and a wide range of downstream benchmarks. Across all evaluations, our models achieve consistent improvements on most regular-context tasks and significant improvements on long-context tasks over Llama 2. Moreover, with a cost-effective instruction tuning procedure that is free of expensive annotation, the presented models can already surpass $\texttt{gpt-3.5-turbo-16k}$&#39;s overall performance on long-context benchmarks. Alongside these results, we provide an in-depth analysis on each individual component of our method. We delve into Llama&#39;s position encodings and discuss its key limitation in modeling long data. We examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths -- ablation results suggest that having abundant long texts in the pretrain dataset is $\textit{not}$ the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.

NAACL 2024

Effective Long-Context Scaling of Foundation Models

data mix recipe

long context

continual pre-training

positional encoding

We present an effective recipe to train strong long-context LLMs that are capable of utilizing massive context windows of up to 32,000 tokens. Our models are built through continual pretraining from Llama 2 checkpoints with longer text sequences and on a dataset where long texts are upsampled. We perform extensive evaluation using language modeling, synthetic context probing tasks, and a wide range of downstream benchmarks. Across all evaluations, our models achieve consistent improvements on most regular-context tasks and significant improvements on long-context tasks over Llama 2. Moreover, with a cost-effective instruction tuning procedure that is free of expensive annotation, the presented models can already surpass $\texttt{gpt-3.5-turbo-16k}$'s overall performance on long-context benchmarks. Alongside these results, we provide an in-depth analysis on each individual component of our method. We delve into Llama's position encodings and discuss its key limitation in modeling long data. We examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths -- ablation results suggest that having abundant long texts in the pretrain dataset is $\textit{not}$ the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.

poster

## Welcome to 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics!
This year, the conference is in Mexico City. NAACL was actually already planned for Mexico City in 2021, but due to the pandemic the entire conference was moved online. This year, finally, we get to go! So it is my sincere pleasure to welcome you to Mexico City, whether in person or virtually. Having the conference in Mexico City is a good opportunity to emphasize that NAACL is our flagship conference for ACL members not only in North America but also in Central and South America, even though NAACL has been bearing “North” in its name. At this year’s conference, we have a theme to match, with a theme track on the Languages of Latin America to showcase the linguistic diversity of the region.
 
The opportunity to present at NAACL should not depend on a researcher’s travel budget, or their family status. This is why it is so important to make virtual participation at NAACL as good an experience as possible – but we want to also provide a good experience for in-person participants. As a community, we are still working out the best way to do that. This year at NAACL, we are trying out a big virtual poster session ahead of the conference, with the hope that this will make make for a lively and interactive experience. At the same time, we are reducing virtual oral presentations, which seem to be particularly tricky to make to work well. A big thanks to the NAACL program chairs and to Luciana Benotti for all their ideas and work to improve the virtual experience. And participants, virtual as well as in-person: Please let us know what worked for you and what didn’t, so we can continue to improve hybrid conferences. 
 
I have been lucky to work with many amazing people. Without their insight, dedication and patience, and without the many hours of work they put in, NAACL would not have been possible. A huge thank you to the program chairs Helena Gomez, Kevin Duh, and Steve Bethard – you are the best! 
 
Finally, I would like to thank all authors, invited speakers and panelists, area chairs and reviewers, the volunteers organizing and chairing sessions, and all attendees, in-person and virtual. Thank you for helping us make NAACL 2024 come to life. 
 
Welcome and hope you all enjoy the conference! 
Katrin Erk 
The University of Texas at Austin 
NAACL-2024 General Chair 
*You can read the full Welcome message in the [Conference Handbook (downloadable)](https://drive.google.com/file/d/1H1NvW0VASQjkSCYgw3mr-3l4yYDSxz6B/view?usp=sharing)*

To access the event page you need to register [**here.**](http://acl.swoogo.com/naacl2024) 
Your access to the event page is limited based on your registration type. If you registered for workshops only, you will gain access to full workshops content on the day of the workshops program.

Please register!

2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics

Learning-to-rank (LTR) algorithms aim to order a set of items according to some criteria. They are at the core of applications such as web search and social media recommendations, and are an area of rapidly increasing interest, with the rise of large language models (LLMs) and the widespread impact of these technologies on society. In this paper, we survey the diverse use cases of LTR methods in natural language processing (NLP) research, looking at previously under-studied aspects such as multilingualism in LTR applications and statistical significance testing for LTR problems. We also consider how large language models are changing the LTR landscape. This survey is aimed at NLP researchers and practitioners interested in understanding the formalisms and best practices regarding the application of LTR approaches in their research.

Methods, Applications, and Directions of Learning-to-Rank in NLP Research

Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized singing explicitly. We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language. We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation that enables text-conditioned vocal range control while keeping melodic accuracy. Furthermore, we explore various experiment settings, including different types of text representations, text encoder fine-tuning, and introducing speech data to alleviate data scarcity, aiming to facilitate further research. Experiments show that our model achieves favorable controlling ability and audio quality. Audio samples are available at http://prompt-singer.github.io .

Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt

The logical information contained in text is of significant importance for logical reasoning. Previous approaches have relied on embedding text into a low-dimensional vector to capture logical information and perform reasoning in Euclidean space. These methods involve constructing special graph architectures that match logical relations or designing data augmentation frameworks by extending texts based on symbolic logic. However, it presents two obvious problems. 1) The logical information reflected in the text exhibits uncertainty that is difficult to represent using a vector. 2) Integrating logical information requires modeling logical operations (such as ∪, ∩, and ¬), while only simple arithmetic operations can be performed in Euclidean space. To address both the problems, we propose Beta-LR, a probabilistic embedding method to capture logical information. Specifically, we embed texts into beta distribution on each dimension to eliminate logical uncertainty. We also define neural operators that enable interpretability and perform logical operations based on the characteristics of the beta distribution. We conduct experiments on two datasets, ReClor and LogiQA, and our Beta-LR achieves competitive results. The experiments demonstrate that our method effectively captures the logical information in text for reasoning purposes. The source code is available at https://github.com/myz12138/Beta-LR.

Beta-LR: Interpretable Logical Reasoning based on Beta Distribution

This study explores the potential of automating clinical coding in Icelandic, a language with limited digital resources, by leveraging over 25 years of electronic health records (EHR) from the Landspitali University Hospital. Traditionally a manual and error-prone task, clinical coding is essential for patient care, billing, and research. Our research delves into the effectiveness of Transformer-based models in automating this process. We investigate various model training strategies, including continued pretraining and model adaptation, under a constrained computational budget. Our findings reveal that the best-performing model achieves competitive results in both micro and macro F1 scores, with label attention contributing significantly to its success. The study also explores the possibility of training on unlabeled data. Our research provides valuable insights into the possibilities of using NLP for clinical coding in low-resource languages, demonstrating that small countries with unique languages and well-segmented healthcare records can achieve results comparable to those in higher-resourced languages.

Applications of BERT Models Towards Automation of Clinical Coding in Icelandic

Reasoning in the presence of idiomatic expressions (IEs) remains a challenging frontier in natural language understanding (NLU). Unlike standard text, the non-compositional nature of an IE makes it difficult for model comprehension, as their figurative or non-literal mean- ing usually cannot be inferred from the constituent words alone. It stands to reason that in these challenging circumstances, pre-trained language models (PTLMs) should make use of the surrounding context to infer additional in- formation about the IE. In this paper, we investigate the utilization of said context for idiomatic reasoning tasks, which is under-explored relative to arithmetic or commonsense reason- ing (Liu et al., 2022; Yu et al., 2023). Preliminary findings point to a surprising observation: general purpose PTLMs are actually negatively affected by the context, as performance almost always increases with its removal. In these scenarios, models may see gains of up to 3.89%. As a result, we argue that only IE-aware models remain suitable for idiomatic reasoning tasks, given the unexpected and unexplainable manner in which general purpose PTLMs reason over IEs. Additionally, we conduct studies to examine how models utilize the context in various situations, as well as an in-depth analysis on dataset formation and quality. Finally, we provide some explanations and insights into the reasoning process itself based on our results.

No Context Needed: Contextual Quandary In Idiomatic Reasoning With Pre-Trained Language Models

Document translation poses a challenge for Neural Machine Translation (NMT) systems. Most document-level NMT systems rely on meticulously curated sentence-level parallel data, assuming flawless extraction of text from documents along with their precise reading order. These systems also tend to disregard additional visual cues such as the document layout, deeming it irrelevant. However, real-world documents often possess intricate text layouts that defy these assumptions. Extracting information from Optical Character Recognition (OCR) or heuristic rules can result in errors, and the layout (e.g., paragraphs, headers) may convey relationships between distant sections of text. This complexity is particularly evident in widely used PDF documents, which represent information visually. This paper addresses this gap by introducing M3T a novel benchmark dataset tailored to evaluate NMT systems on the comprehensive task of translating semi-structured documents. This dataset aims to bridge the evaluation gap in document-level NMT systems, acknowledging the challenges posed by rich text layouts in real-world applications.

M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation

Isotropy is the property that embeddings are uniformly distributed around the origin. Previous work has shown that Transformer embedding spaces are anisotropic, which is called the representation degradation problem. This degradation has been assumed to be inherent to the standard language modeling tasks and to apply to all Transformer models regardless of their architecture. In this work we identify a set of Transformer models with isotropic embedding spaces, the large Pythia models. We examine the isotropy of Pythia models and explore how isotropy and anisotropy develop as a model is trained. We find that anisotropic models do not develop as previously theorized, using our own analysis to show that the large Pythia models optimize their final Layer Norm for isotropy, and provide reasoning why previous theoretical justifications for anisotropy were insufficient. The identification of a set of isotropic Transformer models calls previous assumptions into question, provides a set of models to contrast existing analysis, and should lead to deeper insight into isotropy.

Anisotropy is Not Inherent to Transformers

Generative linguistic steganography attempts to hide secret messages into covertext. Previous studies have generally focused on the statistical differences between the covertext and stegotext, however, ill-formed stegotext can readily be identified by humans. In this paper, we propose a novel zero-shot approach based on in-context learning for linguistic steganography to achieve better perceptual and statistical imperceptibility. We also design several new metrics and reproducible language evaluations to measure the imperceptibility of the stegotext. Our experimental results indicate that our method produces $1.926\times$ more innocent and intelligible stegotext than any other method.

Zero-shot Generative Linguistic Steganography

Recently, contrastive learning has begun to gain popularity in multimodal sentiment analysis (MSA). However, most of existing MSA methods based on contrastive learning lacks more detailed learning of the distribution of sample pairs with different sentiment intensity differences in the contrastive learning representation space. In addition, limited research has been conducted on the fusion of each modality representation obtained by contrastive learning training.In this paper, we propose a novel framework for multimodal sentiment analysis based on Contrastive Learning Guided by Sentiment Intensity (CLGSI). Firstly, the proposed contrastive learning guided by sentiment intensity selects positive and negative sample pairs based on the difference in sentiment intensity and assigns corresponding weights accordingly.Subsequently, we propose a new multimodal representation fusion mechanism, called Global-Local-Fine-Knowledge (GLFK), which extracts common features between different modalities' representations. At the same time, each unimodal encoder output is separately processed by a Multilayer Perceptron (MLP) to extract specific features of each modality. Finally, joint learning of the common and specific features is used to predict sentiment intensity. The effectiveness of CLGSI is assessed on two English datasets, MOSI and MOSEI, as well as one Chinese dataset, SIMS. We achieve competitive experimental results, which attest to the strong generalization performance of our approach. The code for our approach will be released in https://github.com/AZYoung233/CLGSI

CLGSI: A Multimodal Sentiment Analysis Framework based on Contrastive Learning Guided by Sentiment Intensity

Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful. Nevertheless, some human instructions are often malicious or misleading and following them will lead to untruthful and unsafe responses. Previous work rarely focused on understanding how LLMs manage instructions based on counterfactual premises, referred to here as inductive instructions, which may stem from users' false beliefs or malicious intents. In this paper, we aim to reveal the behaviors of LLMs towards inductive instructions and enhance their truthfulness and helpfulness accordingly. Specifically, we first introduce a benchmark of Inductive Instructions (INDust), where the false knowledge is incorporated into instructions in multiple different styles. After extensive human and automatic evaluations, we uncovered a universal vulnerability among LLMs in processing inductive instructions. Additionally, we identified that different inductive styles affect the models' ability to identify the same underlying errors, and the complexity of the underlying assumptions also influences the model's performance. Motivated by these results, we propose Dual-critique prompting to improve LLM robustness against inductive instructions. Our experiments demonstrate that Dual-critique prompting significantly bolsters the robustness of a diverse array of LLMs, even when confronted with varying degrees of inductive instruction complexity and differing inductive styles.

Premium content

Effective Long-Context Scaling of Foundation Models

Downloads

Next from NAACL 2024

Methods, Applications, and Directions of Learning-to-Rank in NLP Research

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES