United States

Transformers are considered conceptually different than the previous generation of state-of-the-art NLP models - recurrent neural networks (RNNs). In this work, we demonstrate that decoder-only transformers can in fact be conceptualized as $\textit{unbounded}$ multi-state RNNs—an RNN variant with unlimited hidden state size.

We further show that transformers can be converted into $\textit{bounded}$ multi-state RNNs by fixing the size of their hidden state, effectively compressing their key-value cache.

We introduce a novel, training-free compression policy - $\textit{T}$oken $\textit{O}$mission $\textit{V}$ia $\textit{A}$ttention (TOVA).

Our experiments with four long range tasks and several LLMs show that TOVA outperforms several baseline compression policies. Particularly, our results are nearly on par with the full model, using in some cases only $\frac{1}{8}$ of the original cache size, which translates to 4.8X higher throughput.

Our results shed light on the connection between transformers and RNNs, and help mitigate one of LLMs&#39; most painful computational bottlenecks---the size of their key-value cache. We will publicly release our code upon publication.

EMNLP 2024

Transformers are Multi-State RNNs

cross-lingual generalization

dialects

low-resource

### 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!

ACL 2024

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.

Transformers are considered conceptually different than the previous generation of state-of-the-art NLP models - recurrent neural networks (RNNs). In this work, we demonstrate that decoder-only transformers can in fact be conceptualized as $\textit{unbounded}$ multi-state RNNs—an RNN variant with unlimited hidden state size.

We further show that transformers can be converted into $\textit{bounded}$ multi-state RNNs by fixing the size of their hidden state, effectively compressing their key-value cache.

We introduce a novel, training-free compression policy - $\textit{T}$oken $\textit{O}$mission $\textit{V}$ia $\textit{A}$ttention (TOVA).

Our experiments with four long range tasks and several LLMs show that TOVA outperforms several baseline compression policies. Particularly, our results are nearly on par with the full model, using in some cases only $\frac{1}{8}$ of the original cache size, which translates to 4.8X higher throughput.

Our results shed light on the connection between transformers and RNNs, and help mitigate one of LLMs' most painful computational bottlenecks---the size of their key-value cache. We will publicly release our code upon publication.

poster

## 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.

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.

While large language models exhibit certain cross-lingual generalization capabilities, they suffer from performance degradation (PD) on unseen closely-related languages (CRLs) and dialects relative to their high-resource language neighbour (HRLN). However, we currently lack a fundamental understanding of what kinds of linguistic distances contribute to PD, and to what extent. Furthermore, studies of cross-lingual generalization are confounded by unknown quantities of CRL language traces in the training data, and by the frequent lack of availability of evaluation data in lower-resource related languages and dialects. To address these issues, we model phonological, morphological, and lexical distance as Bayesian noise processes to synthesize artificial languages that are controllably distant from the HRLN. We analyse PD as a function of underlying noise parameters, offering insights on model robustness to isolated and composed linguistic phenomena, and the impact of task and HRL characteristics on PD. We calculate parameter posteriors on real CRL-HRLN pair data and show that they follow computed trends of artificial languages, demonstrating the viability of our noisers. Our framework offers a cheap solution for estimating task performance on an unseen CRL given HRLN performance using its posteriors, as well as for diagnosing observed PD on a CRL in terms of its linguistic distances from its HRLN, and opens doors to principled methods of mitigating performance degradation.

Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalization

Model fusion research aims to aggregate the knowledge of multiple individual models to enhance performance by combining their weights. In this work, we study the inverse problem: investigating whether model fusion can be used to reduce unwanted knowledge. We investigate the effects of model fusion in three scenarios: the learning of shortcuts, social biases, and memorization of training data in fine-tuned language models. Through experiments covering classification and generation tasks, our analysis highlights that shared knowledge among models is enhanced during model fusion, while unshared knowledge is usually forgotten. Based on this observation, we demonstrate the potential of model fusion as a debiasing tool and showcase its efficacy in addressing privacy concerns associated with language models.

Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion

The fusion of language models (LMs) and knowledge graphs (KGs) is widely used in commonsense question answering, but generating faithful explanations remains challenging. Current methods often overlook path decoding faithfulness, leading to divergence between graph encoder outputs and model predictions. We identify confounding effects and LM-KG misalignment as key factors causing spurious explanations. To address this, we introduce the LM-KG Fidelity metric to assess KG representation reliability and propose the LM-KG Distribution-aware Alignment (LKDA) algorithm to improve explanation faithfulness. Without ground truth, we evaluate KG explanations using the proposed Fidelity-Sparsity Trade-off Curve. Experiments on CommonsenseQA and OpenBookQA show that LKDA significantly enhances explanation fidelity and model performance, highlighting the need to address distributional misalignment for reliable commonsense reasoning.

Towards Faithful Knowledge Graph Explanation Through Deep Alignment in Commonsense Question Answering

Argument relation classification (ARC) identifies supportive, contrasting and neutral relations between argumentative units. The current approaches rely on transformer architectures which have proven to be more effective than traditional methods based on hand-crafted linguistic features. In this paper, we introduce DISARM, which advances the state of the art with a training procedure combining multi-task and adversarial learning strategies. By jointly solving the ARC and discourse marker detection tasks and aligning their embedding spaces into a unified latent space, DISARM outperforms the accuracy of existing approaches.

Argument Relation Classification through Discourse Markers and Adversarial Training

Pre-trained transformers such as BERT have been shown to be effective in many natural language tasks. However, they are under-explored for character-level sequence to sequence tasks. In this work, we investigate pre-training transformers for the character-level task of morphological inflection in several languages. We compare various training setups and secondary tasks where unsupervised data taken directly from the target task is used. We show that training on secondary unsupervised tasks increases inflection performance even without any external data, suggesting that models learn from additional unsupervised tasks themselves---not just from additional data. We also find that this does not hold true for specific combinations of secondary task and training setup, which has interesting implications for denoising objectives in character-level tasks.

Getting The Most Out of Your Training Data: Exploring Unsupervised Tasks for Morphological Inflection

While natural language inference (NLI) has emerged as a prominent task for evaluating a model's capability to perform natural language understanding, creating large benchmarks for training deep learning models imposes a significant challenge since it requires extensive human annotations. To overcome this, we propose to construct pseudo-generated samples (premise-hypothesis pairs) using class-specific fine-tuned large language models (LLMs) thereby reducing the human effort and the costs in annotating large amounts of data. However, despite the impressive performance of LLMs, it is necessary to verify that the pseudo-generated labels are actually correct. Towards this goal, in this paper, we propose VerifyMatch, a semi-supervised learning (SSL) approach in which the LLM pseudo-labels guide the training of the SSL model and, at the same time, the SSL model acts as a verifier of the LLM-generated data. In our approach, we retain all pseudo-labeled samples, but to ensure unlabeled data quality, we further propose to use MixUp whenever the verifier does not agree with the LLM-generated label or when they both agree on the label but the verifier has a low confidence---lower than an adaptive confidence threshold. We achieve competitive accuracy compared to strong baselines for NLI datasets in low-resource settings.

VerifyMatch: A Semi-Supervised Learning Paradigm for Natural Language Inference with Confidence-Aware MixUp

Large language models (LLMs), especially when instruction-tuned for chat, have become part of our daily lives, freeing people from the process of searching, extracting, and integrating information from multiple sources by offering a straightforward answer to a variety of questions in a single place. Unfortunately, in many cases, LLM responses are factually incorrect, which limits their applicability in real-world scenarios. As a result, research on evaluating and improving the factuality of LLMs has attracted a lot of research attention recently. In this survey, we critically analyze existing work with the aim to identify the major challenges and their associated causes, pointing out to potential solutions for improving the factuality of LLMs, and analyzing the obstacles to automated factuality evaluation for open-ended text generation. We further offer an outlook on where future research should go.

Factuality of Large Language Models in the Year 2024

Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain classes in the dataset. Recent work proposes automatic methods for identifying and explaining systematic biases using keywords. We introduce DISCERN, a framework for interpreting systematic biases in text classifiers using language explanations. DISCERN iteratively generates precise natural language descriptions of systematic errors by employing an interactive loop between two large language models. Finally, we use the descriptions to improve classifiers by augmenting classifier training sets with synthetically generated instances or annotated examples via active learning. On three text-classification datasets, we demonstrate that language explanations from our framework induce consistent performance improvements that go beyond what is achievable with exemplars of systematic bias. Finally, in human evaluations, we show that users can interpret systematic biases more effectively (by over 25% relative) and efficiently when described through language explanations as opposed to cluster exemplars.

DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers

We explore the alignment of values in Large Language Models (LLMs) with specific age groups, leveraging data from the World Value Survey across thirteen categories. 
Through a diverse set of prompts tailored to ensure response robustness, we find a general inclination of LLM values towards younger demographics, especially when compared to the US population. 
Although a general inclination can be observed, we also found that this inclination toward younger groups can be different across different value categories. 
Additionally, we explore the impact of incorporating age identity information in prompts and observe challenges in mitigating value discrepancies with different age cohorts. Our findings highlight the age bias in LLMs and provide insights for future work. Materials for our analysis will be available via \url{https://github.com/anonymous}

The Generation Gap: Exploring Age Bias Underlying in the Value Systems of Large Language Models

Social biases such as gender or racial biases have been reported in language models (LMs), including Masked Language Models (MLMs). Given that MLMs are continuously trained with increasing amounts of additional data collected over time, an important yet unanswered question is how the social biases encoded with MLMs vary over time. In particular, the number of social media users continues to grow at an exponential rate, and it is a valid concern for the MLMs trained specifically on social media data whether their social biases (if any) would also amplify over time. To empirically analyse this problem, we use a series of MLMs pretrained on chronologically ordered temporal snapshots of corpora. Our analysis reveals that, although social biases are present in all MLMs, most types of social bias remain relatively stable over time (with a few exceptions). To further understand the mechanisms that influence social biases in MLMs, we analyse the temporal corpora used to train the MLMs. Our findings show that some demographic groups, such as male, obtain higher preference over the other, such as female on the training corpora constantly.

Downloads

Next from EMNLP 2024

Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalization

Similar lecture

On Efficiently Representing Regular Languages as RNNs