Singapore

In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a pre-trained dense retrieval model to bypass this limitation, giving the model only a partial view of the full label space for each inference call. Testing with recent open-source LLMs (OPT, LLaMA), we set new state of the art performance in few-shot settings for three common intent classification datasets, with no fine-tuning. We also surpass fine-tuned performance on fine-grained sentiment classification in certain cases. We analyze the performance across number of in-context examples and different model scales, showing that larger models are necessary to effectively make use of larger context lengths for ICL. By running several ablations, we analyze the model&#39;s use of: a) the similarity of the in-context examples to the current input, b) the semantic content of the class names, and c) the correct correspondence between examples and labels. We demonstrate that all three are needed to varying degrees depending on the domain, contrary to certain recent works.

EMNLP 2023

In-Context Learning for Text Classification with Many Labels

in-context learning

intent classification

retrieval

sentiment analysis

text classification

intent detection

sentiment classification

dialogue

### 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)

In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a pre-trained dense retrieval model to bypass this limitation, giving the model only a partial view of the full label space for each inference call. Testing with recent open-source LLMs (OPT, LLaMA), we set new state of the art performance in few-shot settings for three common intent classification datasets, with no fine-tuning. We also surpass fine-tuned performance on fine-grained sentiment classification in certain cases. We analyze the performance across number of in-context examples and different model scales, showing that larger models are necessary to effectively make use of larger context lengths for ICL. By running several ablations, we analyze the model's use of: a) the similarity of the in-context examples to the current input, b) the semantic content of the class names, and c) the correct correspondence between examples and labels. We demonstrate that all three are needed to varying degrees depending on the domain, contrary to certain recent works.

workshop paper

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

GQG is a dataset with 18,360 prompts consisting of various quantifier expressions to evaluate the generalization abilities of language models. GQG dataset enables research on different axes of generalization, such as token frequency.

GQG: Generalized Quantifier Generalization - A Dataset for Evaluating Quantifier Semantics Understanding in Language Models

This paper presents an innovative data augmentation framework with data quality control designed to enhance the robustness of Question Answering (QA) models in low-resource languages, particularly Thai. Recognizing the challenges posed by the scarcity and quality of training data, we leverage data augmentation techniques in both monolingual and cross-lingual settings. Our approach augments and enriches the original dataset, thereby increasing its linguistic diversity and robustness. We evaluate the robustness of our framework on Machine Reading Comprehension, and the experimental results illustrate the potential of data augmentation to effectively increase training data and improve model generalization in low-resource language settings, offering a promising direction for the data augmentation manner.

Cross-Lingual Data Augmentation For Thai Question-Answering | VIDEO

Compositional generalisation (CG), in NLP and in machine learning more generally, has been assessed mostly using artificial datasets. It is important to develop benchmarks to assess CG also in real-world natural language tasks in order to understand the abilities and limitations of systems deployed in the wild. To this end, our GenBench Collaborative Benchmarking Task submission utilises the distribution-based compositionality assessment (DBCA) framework to split the Europarl translation corpus into a training and a test set in such a way that the test set requires compositional generalisation capacity. Specifically, the training and test sets have divergent distributions of dependency relations, testing NMT systems' capability of translating dependencies that they have not been trained on. This is a fully-automated procedure to create natural language compositionality benchmarks, making it simple and inexpensive to apply it further to other datasets and languages. The code and data for the experiments is available at https://github.com/aalto-speech/dbca.

On using distribution-based compositionality assessment to evaluate compositional generalisation in machine translation

Semantic parsing plays a pivotal role in advancing the accessibility of human-computer interaction on a large scale. Spider, a widely recognized dataset for text-to-SQL, contains a wide range of natural language (NL) questions in English and corresponding SQL queries. 
Original splits of Spider and its adapted to Russian language and improved version, PAUQ, assume independence and identical distribution of training and testing data (i.i.d split). In this work, we propose a target length split and multilingual i.i.d split to measure compositionality and cross-language generalization. We present experimental results of popular text-to-SQL models on original, multilingual, and target length splits. We also construct a context-free grammar for the evaluation of compositionality in text-to-SQL in an out-of-distribution setting. We make the splits publicly available on HuggingFace hub via https://huggingface.co/datasets/composite/pauq.

Shifted PAUQ: Distribution shift in text-to-SQL

Just like the previous generation of task-tuned models, large language models (LLMs) that are adapted to tasks via prompt-based methods like in-context-learning (ICL) perform well in some setups but not in others. This lack of consistency in prompt-based learning hints at a lack of robust generalisation. We here introduce the ICL consistency test – a contribution to the GenBench collaborative benchmark task (CBT) which evaluates how consistent a model makes predictions across many different setups while using the same data. The test is based on different established natural language inference tasks. We provide preprocessed data constituting 96
different ‘setups’ and a metric that estimates model consistency across these setups. The metric is provided on a fine-grained level to understand what properties of a setup render predictions unstable and on an aggregated level to compare overall model consistency. We conduct an empirical analysis of eight state-of-the-art models, and our consistency metric reveals how all tested LLMs lack robust generalisation.

The ICL consistency test

Large language model (LLMs) have demonstrated promising performance in many tasks. However, before deploying them in real-world healthcare applications, these models need to be assessed on generalizability and robustness. We evaluate and compare six different LLMs and conclude that, even though the two concepts seem similar, the models do not necessarily demonstrate the same capability in both generalization and robustness.

Generalizability and Robustness of Large Language Models Detecting Alzheimer’s Disease from Speech

Multilingual large-scale Pretrained Language Models (PLMs) have been shown to store considerable amounts of factual knowledge, but large variations are observed across languages. With the ultimate goal of ensuring that users with different language backgrounds obtain consistent feedback from the same model, we study the cross-lingual consistency (CLC) of factual knowledge in various multilingual PLMs. To this end, we propose a Ranking-based Consistency (RankC) metric to evaluate knowledge consistency across languages independently from accuracy. Using this metric, we conduct an in-depth analysis of the determining factors for CLC, both at model level and at language-pair level. Among other results, we find that increasing model size leads to higher factual probing accuracy in most languages, but does not improve cross-lingual consistency. Finally, we conduct a case study on CLC when new factual associations are inserted in the PLMs via model editing. Results on a small sample of facts inserted in English reveal a clear pattern whereby the new piece of knowledge transfers only to languages with which English has a high RankC score.

Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models

NLP models often rely on superficial cues known as dataset biases to achieve impressive performance, and can fail on examples where these biases do not hold. Recent work sought to develop robust, unbiased models by filtering biased examples from training sets. In this work, we argue that such filtering can obscure the true capabilities of models to overcome biases, which might never be removed in full from the dataset. We suggest that in order to drive the development of models robust to subtle biases, dataset biases should be amplified in the training set. We introduce an evaluation framework defined by a bias-amplified training set and an anti-biased test set, both automatically extracted from existing datasets. Experiments across four datasets and three models show that our framework is substantially more challenging for models than the original data splits in both fine-tuning and few-shot settings. We hope our work will guide the development of robust models that do not rely on superficial biases and correlations.

Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases

Compositional generalisation is the ability to compose novel combinations from known parts. Recent works have investigated whether neural models are able to achieve such generalisation e.g. handle novel syntactic combinations of known semantic phrases. We apply this idea to morphological composition – the ability to compose the meaning of a word from its constituent morphemes. Our experimental setting is the task of machine translation from English to the Nguni languages, a related group of South African languages that are highly agglutinative - making them ideal for testing morphological modelling. We propose an algorithm for constructing train/test splits with similar morpheme distributions, but diverging word distributions. This allows us to evaluate whether models can handle novel combinations of known morphemes (previously unseen words consisting of previously seen morphemes). We compare results of neural machine translation models using different subword segmenters. All models see performance drops on more challenging evaluation sets, showing that current approaches do not reliably learn morphological composition. Methods that optimise subword segmentation for translation performance (DPE and SSMT) exhibit better performance than standard subword methods (BPE and ULM).

Downloads

Next from EMNLP 2023

GQG: Generalized Quantifier Generalization - A Dataset for Evaluating Quantifier Semantics Understanding in Language Models

Similar lecture

Revisiting In-Context Learning with Long Context Language Models

.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 EMNLP 2023

GQG: Generalized Quantifier Generalization - A Dataset for Evaluating Quantifier Semantics Understanding in Language Models

Similar lecture

Revisiting In-Context Learning with Long Context Language Models

Downloads