Challenge: valence is encoded in meaningful ways in large language models and in some LLMs, pseudowords affect the representation of whole sentences similarly to words.
Approach: They investigate how LLMs represent valence, a key semantic attribute, and how they deal with contextualisation of pseudowords in sentences.
Outcome: The results show that the models represent valence, a key semantic attribute, in sentences and in context, and that they handle the contextualisation of pseudowords differently.

Similar Papers

Understanding Subword Compositionality of Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) take sequences of subwords as input, requiring them to compose subword representations into meaningful word-level representations.
Approach: They propose to probe how large language models compose subword information . they find structural similarity, semantic decomposability, and form retention are key aspects .
Outcome: The proposed models can be classified into three distinct groups, the authors show . they show that they can achieve great performance when probing layer by layer their sensitivity to semantic decompositionality .
Unlike “Likely”, “Unlike” is Unlikely: BPE-based Segmentation hurts Morphological Derivations in LLMs (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) use subword vocabularies to process and generate text.
Approach: They find that Large Language Models (LLMs) perform poorly at handling some types of affixations because subwords are marked as initial- or intra-word .
Outcome: The largest models trained on enough data can mitigate this tendency because initial- and intra-word embeddings are aligned; in-context learning also helps when all examples are selected in a consistent way; but only morphological segmentation can achieve a near-perfect accuracy.
Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymy (2021.acl-long)

Copied to clipboard

Challenge: Existing models that represent different senses of words in context are not accurate for polysemous words.
Approach: They propose a multilingual dataset that evaluates the ability of models to accurately represent different lexical-semantic relations such as homonymy and synonymy.
Outcome: The proposed models can disambiguate homonyms in context, but fail to represent words with different senses when occurring in similar sentences.
Patterns of Polysemy and Homonymy in Contextualised Language Models (2021.findings-emnlp)

Copied to clipboard

Challenge: a recent study has focused on homonymy, a variety of multiplicity of meanings exemplified by word forms with unrelated meanings.
Approach: They investigate the extent to which contextualised embeddings reflect traditional distinctions of polysemy and homonymy.
Outcome: The proposed model shows that it can distinguish between polysemy and homonymy . it shows that the model fails to replicate the results of the human-annotated dataset .
Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics (2024.findings-acl)

Copied to clipboard

Challenge: Existing research suggests that contextual representations of large language models exhibit subpar performance in downstream tasks, struggling to fully capture the semantic nuances of words.
Approach: They investigate the bottom-up evolution of lexical semantics for a popular LLM . they probing its hidden states at the end of each layer using a contextualized word identification task .
Outcome: The proposed model is able to encode lexical semantics in lower layers while achieving weaker induction in higher layers.
Exploring Layer-wise Representations of English and Chinese Homonymy in Pre-trained Language Models (2025.findings-acl)

Copied to clipboard

Challenge: lexical ambiguity can arise due to the misunderstanding of its multiple senses.
Approach: They propose to use part of speech to examine homonyms in Chinese and English . they find no universal layer depth excels in differentiating homnomial representations .
Outcome: The proposed model improves contextualization of homonym representations in Chinese . the results challenge the simplistic understanding of their inner workings, the authors say .
Deep Generative Model for Joint Alignment and Word Representation (N18-1)

Copied to clipboard

Challenge: EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments.
Approach: They exploit translation as a distributional context and embed words as posterior probability densities, rather than point estimates, which allows them to compare words in context using a measure of overlap between distributions.
Outcome: The proposed model performs on a range of lexical semantics tasks and achieves competitive results on benchmarks including natural language inference, paraphrasing, and text similarity.
CUTE: Measuring LLMs’ Understanding of Their Tokens (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) perform well on a wide variety of tasks, authors say . they lack direct access to characters, which can be difficult to generalize to new languages .
Approach: They propose a benchmark to test the orthographic knowledge of Large Language Models . they find that most LLMs seem to know the spelling of their tokens - yet fail to manipulate text .
Outcome: The proposed benchmark tests the orthographic knowledge of large language models . it finds that most LLMs seem to know the spelling of their tokens, but fail to manipulate text .
Putting Words in Context: LSTM Language Models and Lexical Ambiguity (P19-1)

Copied to clipboard

Challenge: In language, a word can contribute a very different meaning depending on the context . lexical ambiguity involves both morphosyntactic and semantic aspects .
Approach: They propose a method to probe hidden representations for lexical and contextual information about words.
Outcome: The proposed method shows that both types of information are represented to a large extent, but there is room for improvement for contextual information.
LLM See, LLM Do: Leveraging Active Inheritance to Target Non-Differentiable Objectives (2024.emnlp-main)

Copied to clipboard

Challenge: Historically, high-quality labeled data has been costly to curate due to scarcity of available data and financial cost.
Approach: They characterize the impact of passive inheritance of model properties by studying how the source of synthetic data shapes models’ internal biases, calibration and preferences, and their generations’ textual attributes.
Outcome: The proposed model inheritance can increase lexical diversity or reduce toxicity.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations