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

**Workshop Organizers:** Dieuwke Hupkes, Verna Dankers, Koustuv Sinha, Amirhossein Kazemnejad, Christos Christodoulopoulos, Ryan Cotterell and Elia Bruni
 *Coffee Break 10:30 am* 
*Lunch Break 12:30 pm* 
*Coffee Break 3:30 pm* [**Workshop Website**](https://genbench.org/workshop/) The ability to generalise is one of the primary desiderata of natural language processing (NLP). Yet, how "good generalisation" should be defined and evaluated is not well understood, nor are there common standards to evaluate generalisation. As a consequence, newly proposed models are usually not systematically tested for their ability to generalise. GenBench's mission is to make state-of-the-art generalisation testing the new status-quo in NLP. As a first step, we present a generalisation taxonomy, describing the underlying building blocks of generalisation in NLP. We use the taxonomy to do an elaborate review of over 400 generalisation papers, and we make recommendations for promising areas for the future. 
[**Keynote 1, by Anna Rogers**](https://genbench.org/workshop_programme/#0915-1000-am--keynote-1-by-anna-rogers) [**Keynote 2, by Adina Williams**](https://genbench.org/workshop_programme/#1115-1200-pm--keynote-2-by-adina-williams) [**Keynote 3, by Tatsunori Hashimoto**](https://genbench.org/workshop_programme/#1400-1445-pm--keynote-3-by-tatsunori-hashimoto) 
[**Schedule**](https://genbench.org/workshop_programme/)

 [**Go to Gather**](https://app.gather.town/app/ROH1myZvp9ba7a3C/EMNLP2023?spawnToken=_5ieSSlxSvuKGu7FtBcT)

W04: GenBench: The first workshop on generalisation (benchmarking) in NLP

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.

Lucas Weber

1

SHORT BIO

Presentations

The ICL consistency test

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES