# WUGNECTIVES: Novel Entity Inferences of Language Models from Discourse Connectives

arXiv: https://arxiv.org/abs/2510.09556 · HTML: https://mlsanity.com/paper/2510.09556/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 62 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 14 of 14)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research](https://mlsanity.com/paper/2402.00159/) (2024)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color](https://mlsanity.com/paper/2109.06129/) (2021)
- [ASER: A Large-scale Eventuality Knowledge Graph](https://mlsanity.com/paper/1905.00270/) (2019)
- [minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models](https://mlsanity.com/paper/2203.13112/) (2022)
- [Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models](https://mlsanity.com/paper/2405.09605/) (2024)
- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [Discourse Probing of Pretrained Language Models](https://mlsanity.com/paper/2104.05882/) (2021)
- [Pragmatic competence of pre-trained language models through the lens of discourse connectives](https://mlsanity.com/paper/2109.12951/) (2021)
- [Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models](https://mlsanity.com/paper/2105.03495/) (2021)
- [WinoDict: Probing language models for in-context word acquisition](https://mlsanity.com/paper/2209.12153/) (2022)
- [Characterizing the Role of Similarity in the Property Inferences of Language Models](https://mlsanity.com/paper/2410.22590/) (2024)

## Built on by (most cited first, 2 of 2)

- [Would you still call this Dax? Novel Visual References in VLMs and Humans](https://mlsanity.com/paper/2606.05409/) (2026)
- [Not Just an Evaluation: A Case Study of Discourse Particle Sensitivity in Language Models](https://mlsanity.com/paper/2610.13794/) (2026)

## Abstract (arXiv)

The role of world knowledge has been particularly crucial to predict the discourse connective that marks the discourse relation between two arguments, with language models (LMs) being generally successful at this task. We flip this premise in our work, and instead study the inverse problem of understanding whether discourse connectives can inform LMs about the world. To this end, we present WUGNECTIVES, a dataset of 8,880 stimuli that evaluates LMs' inferences about novel entities in contexts where connectives link the entities to particular attributes. On investigating 17 different LMs at various scales, and training regimens, we found that tuning an LM to show reasoning behavior yields noteworthy improvements on most connectives. At the same time, there was a large variation in LMs' overall performance across connective type, with all models systematically struggling on connectives that express a concessive meaning. Our findings pave the way for more nuanced investigations into the functional role of language cues as captured by LMs. We release WUGNECTIVES at https://github.com/kanishkamisra/wugnectives