United States

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient approach to learning ASR and TTS jointly via a multi-task learning objective and shared parameters. Our evaluation demonstrates that
the performance of our multi-task model is comparable to that of individually trained models while significantly saving
computational and memory costs ($\sim$50\% reduction in the total number of parameters required for the two tasks combined). We experiment with English as a resource-rich language, and Arabic as a relatively low-resource language due to shortage of TTS data. Our models are trained with publicly available data, and both the training code and model checkpoints are openly available for further research.

EMNLP 2024

STTATTS: Unified Speech-To-Text And Text-To-Speech Model

conformal uncertainty criterion

conformal prediction

uncertainty quantification

### 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**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

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.

Please register!

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.

Traditional benchmarking in NLP typically involves using static, held-out test sets and calculating aggregated statistics based on diverse examples. However, this approach often results in an overestimation of performance and lacks the ability to offer comprehensive, interpretable, and dynamic assessments of NLP models. Recently, works like DynaBench and Checklist have addressed these limitations through behavioral testing of NLP models with test types generated by a multi-step human-annotated pipeline. Unfortunately, manually creating a variety of test types requires significant human labor, thus weakening efficiency. In this work, we propose SynthEval, a hybrid behavioral testing framework that leverages large language models (LLMs) to generate a wide range of test types for a comprehensive evaluation of NLP models. The SynthEval framework first generates sentences via LLMs using controlled generation, and then identifies challenging examples by comparing the predictions made by LLMs with task-specific NLP models. In the last stage, human experts investigate the challenging examples, manually design templates, and identify the types of failures the task-specific models consistently exhibit. We apply SynthEval to two classification tasks and show that our framework is effective in identifying weaknesses of strong models on these tasks.

SynthEval: Hybrid Behavioral Testing of NLP Models with Synthetic Evaluation

Multiple choice question answering tasks evaluate the reasoning, comprehension, and mathematical abilities of Large Language Models (LLMs). While existing benchmarks employ automatic translation for multilingual evaluation, this approach is error-prone and potentially introduces culturally biased questions, especially in social sciences. We introduce the first multitask, multiple-choice Turkish QA benchmark, TurkishMMLU, to evaluate LLMs' understanding of the Turkish language. TurkishMMLU includes over 10,000 questions, covering 9 different subjects from Turkish high-school education curricula. These questions are written by curriculum experts, suitable for the high-school curricula in Turkey, covering subjects ranging from natural sciences and math questions to more culturally representative topics such as Turkish Literature and the history of the Turkish Republic. We evaluate over 20 LLMs, including multilingual open-source (e.g., Gemma, Llama, MT5), closed-source (GPT 4o, Claude, Gemini), and Turkish-adapted (e.g., Trendyol) models. We provide an extensive evaluation, including zero-shot and few-shot evaluation of LLMs, chain-of-thought reasoning, and question difficulty analysis along with model performance. We provide an in-depth analysis of the Turkish capabilities and limitations of current LLMs to provide insights for future LLMs for the Turkish language. We publicly release our code for the dataset and evaluation: https://github.com/ArdaYueksel/TurkishMMLU}

TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish

Understanding knowledge mechanisms in Large Language Models (LLMs) is crucial for advancing towards trustworthy AGI. This paper reviews knowledge mechanism analysis from a novel taxonomy including knowledge utilization and evolution. Knowledge utilization delves into the mechanism of memorization, comprehension and application, and creation. Knowledge evolution focuses on the dynamic progression of knowledge within individual and group LLMs. Moreover, we discuss what knowledge LLMs have learned, the reasons for the fragility of parametric knowledge, and the potential dark knowledge (hypothesis) that will be challenging to address. We hope this work can help understand knowledge in LLMs and provide insights for future research.

Knowledge Mechanisms in Large Language Models: A Survey and Perspective

Large language models (LLMs) are utilized in various studies, and they also demonstrate a potential to function independently as a recommendation model. Nevertheless, training sequences and text labels modifies LLMs' pre-trained weights, diminishing their inherent strength in constructing and comprehending natural language sentences. In this study, we propose a reconstruction-based LLM recommendation model (ReLRec) that harnesses the feature extraction capability of LLMs, while preserving LLMs' sentence generation abilities. We reconstruct the user and item pseudo-labels generated from user reviews, while training on sequential data, aiming to exploit the key features of both users and items. Experimental results demonstrate the efficacy of label reconstruction in sequential recommendation tasks.

Enhancing Large Language Model Based Sequential Recommender Systems with Pseudo Labels Reconstruction

In this paper, we compare general-purpose models, $\texttt{GPT-4-Turbo}$ and $\texttt{Llama-3-8b}$, with special-purpose models—$\texttt{XLM-Roberta-large}$, $\texttt{mT5-large}$, and $\texttt{Llama-3-8b}$—that have been fine-tuned on specific tasks. We focus on seven classification and seven generation tasks to evaluate the performance of these models on Urdu language. Urdu has 70 million native speakers, yet it remains underrepresented in Natural Language Processing (NLP). Despite the frequent advancements in Large Language Models (LLMs), their performance in low-resource languages, including Urdu, still needs to be explored. We also conduct a human evaluation for the generation tasks and compare the results with the evaluations performed by $\texttt{GPT-4-Turbo}$, $\texttt{Llama-3-8b}$ and $\texttt{Claude 3.5 Sonnet}$. We find that special-purpose models consistently outperform general-purpose models across various tasks. We also find that the evaluation done by $\texttt{GPT-4-Turbo}$ for generation tasks aligns more closely with human evaluation compared to the evaluation done by $\texttt{Llama-3-8b}$. This paper contributes to the NLP community by providing insights into the effectiveness of general and specific-purpose LLMs for low-resource languages.

Generalists vs. Specialists: Evaluating Large Language Models for Urdu

Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs). Traditionally, training these models relies on extensive human-annotated preference data, which poses significant challenges in terms of scalability and cost. To overcome these limitations, we propose Semi-Supervised Reward Modeling (SSRM), an approach that enhances RM training using unlabeled data. Given an unlabeled dataset, SSRM involves three key iterative steps: pseudo-labeling unlabeled examples, selecting high-confidence examples through a confidence threshold, and supervised finetuning on the refined dataset. Across extensive experiments on various model configurations, we demonstrate that SSRM significantly improves reward models without incurring additional labeling costs. Notably, SSRM can achieve performance comparable to models trained entirely on labeled data of equivalent volumes. Overall, SSRM substantially reduces the dependency on large volumes of human-annotated data, thereby decreasing the overall cost and time involved in training effective reward models.

Semi-Supervised Reward Modeling via Iterative Self-Training

Demonstration selection, the process of selecting examples used in prompts, plays a critical role in in-context learning. 
This paper explores demonstration selection methods for data-to-text tasks that involve numerical time series data as inputs.
Previously developed demonstration selection methods primarily focus on textual inputs, often relying on embedding similarities of textual tokens to select similar instances from an example bank. 
However, this approach may not be suitable for numerical time series data.
To address this issue, we propose two novel selection methods: (1) sequence similarity-based selection using various similarity measures, and (2) task-specific knowledge-based selection.
From our experiments on two benchmark datasets, we found that our proposed models significantly outperform baseline selections and often surpass fine-tuned models. We also found that scale-invariant similarity measures such as Pearson's correlation work better than scale-variant measures such as Euclidean distance.
Manual evaluation by human judges also confirms that our proposed methods outperform conventional methods.

Few-shot Selections for Numerical Time Series Data-to-Text

Parameter Efficient Fine-Tuning (PEFT) offers an efficient solution for fine-tuning large pretrained language models for downstream tasks. However, most PEFT strategies are manually designed, often resulting in suboptimal performance. Recent automatic PEFT approaches aim to address this but face challenges such as search space entanglement, inefficiency, and lack of integration between parameter budgets and search processes. To overcome these issues, we introduce a novel Budget-guided Iterative search strategy for automatic PEFT (BIPEFT), significantly enhancing search efficiency. BIPEFT employs a new iterative search strategy to disentangle the binary module and rank dimension search spaces. Additionally, we design early selection strategies based on parameter budgets, accelerating the learning process by gradually removing unimportant modules and fixing rank dimensions. Extensive experiments on public benchmarks demonstrate the superior performance of BIPEFT in achieving efficient and effective PEFT for downstream tasks with a low parameter budget.

BIPEFT: Budget-Guided Iterative Search for Parameter Efficient Fine-Tuning of Large Pretrained Language Models

Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT) method, significantly enhances the training efficiency by updating only a small portion of the weights in Large Language Models (LLMs). Recently, weight-only quantization techniques have also been applied to LoRA methods to reduce the memory footprint of fine-tuning. However, applying weight-activation quantization to the LoRA pipeline is under-explored, and we observe substantial performance degradation primarily due to the presence of activation outliers. In this work, we propose RoLoRA, the first LoRA-based scheme to apply rotation for outlier elimination, and then fine-tune rotated outlier-free LLMs for effective weight-activation quantization. Different from previous work tackling the outlier challenges from a post-training perspective, we propose rotation-aware fine-tuning to eliminate and preserve the outlier-free characteristics brought by rotation operations. RoLoRA can improve low-bit LoRA convergence and post-training quantization robustness in weight-activation settings. RoLoRA is evaluated across various LLM series (LLaMA2, LLaMA3, LLaVA-1.5), tasks, and quantization settings, achieving up to 29.5% absolute accuracy gain of 4-bit weight-activation quantized LLaMA2-13B on commonsense reasoning tasks compared to LoRA baseline. We further demonstrate its effectiveness on Large Multimodal Models (LMMs) and prove the compatibility with advanced LoRA variants.

RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization

Given the prompt "Rome is in", can we steer a language model to flip its prediction of an incorrect token "France" to a correct token "Italy" by only multiplying a few relevant activation vectors with scalars? We argue that successfully intervening on a model is a prerequisite for interpreting its internal workings. Concretely, we establish a three-term objective: a successful intervention should flip the correct with the wrong token and vice versa (effectiveness), and leave other tokens unaffected (faithfulness), all while being sparse (minimality). Using gradient-based optimization, this objective lets us learn (and later evaluate) a specific kind of efficient and interpretable intervention: activation scaling only modifies the signed magnitude of activation vectors to strengthen, weaken, or reverse the steering directions already encoded in the model. On synthetic tasks, this intervention performs comparably with steering vectors in terms of effectiveness and faithfulness, but is much more minimal allowing us to pinpoint interpretable model components. We evaluate activation scaling from different angles, compare performance on different datasets, and make activation scalars a learnable function of the activation vectors themselves to generalize to varying-length prompts.

Downloads

Next from EMNLP 2024

SynthEval: Hybrid Behavioral Testing of NLP Models with Synthetic Evaluation

Similar lecture

SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Models