Recent scholarship on reasoning in LLMs has supplied evidence of impressive performance and flexible adaptation to machine generated or human critique. Nonmonotonic reasoning, crucial to human cognition for navigating the real world, remains a challenging, yet understudied task. In this work, we study nonmonotonic reasoning capabilities of seven state-of-the-art LLMs in one abstract and one commonsense reasoning task featuring generics, such as `Birds fly', and exceptions, 'Penguins don't fly' (see Fig. 1). 
While LLMs exhibit reasoning patterns in accordance with human nonmonotonic reasoning abilities, they fail to maintain stable beliefs on truth conditions of generics at the addition of supporting examples ('Owls fly') or unrelated information ('Lions have manes').
Our findings highlight pitfalls in attributing human reasoning behaviours to LLMs as long as consistent reasoning remains elusive.

Are LLMs classical or nonmonotonic reasoners? Lessons from generics

Large Language Models (LLMs) exhibit impressive performance on a range of NLP tasks, due to the general-purpose linguistic knowledge acquired during pretraining. Existing model interpretability research (Tenney et al., 2019) suggests that a linguistic hierarchy emerges in the LLM layers, with lower layers better suited to solving syntactic tasks and higher layers employed for semantic processing. Yet, little is known about how encodings of different linguistic phenomena interact within the models and to what extent processing of linguistically-related categories relies on the same, shared model representations. In this paper, we propose a framework for testing the joint encoding of linguistic categories in LLMs. Focusing on syntax, we find evidence of joint encoding both at the same (related part-of-speech (POS) classes) and different (POS classes and related syntactic dependency relations) levels of linguistic hierarchy. Our cross-lingual experiments show that the same patterns hold across languages in multilingual LLMs.

Probing LLMs for Joint Encoding of Linguistic Categories

The latest generation of LLMs can be prompted to achieve impressive zero-shot or few-shot performance in many NLP tasks. However, since performance is highly sensitive to the choice of prompts, considerable effort has been devoted to crowd-sourcing prompts or designing methods for prompt optimisation. Yet, we still lack a systematic understanding of how linguistic properties of prompts correlate with the task performance. In this work, we investigate how LLMs of different sizes, pre-trained and instruction-tuned, perform on prompts that are semantically equivalent, but vary in linguistic structure. We investigate both grammatical properties such as mood, tense, aspect and modality, as well as lexico-semantic variation through the use of synonyms. Our findings contradict the common assumption that LLMs achieve optimal performance on prompts which reflect language use in pretraining or instruction-tuning data. Prompts transfer poorly between datasets or models, and performance cannot generally be explained by perplexity, word frequency, word sense ambiguity or prompt length. Based on our results, we put forward a proposal for a more robust and comprehensive evaluation standard for prompting research.

The language of prompting: What linguistic properties make a prompt successful?

This poster session includes Main Conference posters, TACL and CL , and Demos.

In-Person Poster Session 6

poster

### 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.

**Are you attending this poster session virtually?** 
In-person printed posters are available for in-person attendees only.
 
**Are you attending this poster session in person?** 
Hybrid posters are displayed in the East Foyer.

PS7 (In-person) Posters, Demo, Industry, Findings

**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

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

PS6 (In-person) Posters, Demo, Industry, Findings

**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)

Alina Leidinger

4

SHORT BIO

Presentations

Are LLMs classical or nonmonotonic reasoners? Lessons from generics

Probing LLMs for Joint Encoding of Linguistic Categories

The language of prompting: What linguistic properties make a prompt successful?

The language of prompting: What linguistic properties make a prompt successful?

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES