| Challenge: | Large pre-trained language models often learn spurious domain-specific words to make predictions. |
| Approach: | They propose a model that learns from human annotated explanations of stylistic features and jointly predicts them as model explanations. |
| Outcome: | The proposed model can provide human like stylistic lexical explanations without sacrificing performance on in-domain and out-of-domain datasets. |
Similar Papers
Learning Interpretable Style Embeddings via Prompting LLMs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has treated the style of a text as separable from the content. |
| Approach: | They use prompting to perform stylometry on a large number of texts to generate a synthetic stylometric dataset. |
| Outcome: | The proposed model trains human-interpretable representations on a large stylometric dataset and a linguistic model for style representation learning. |
CLIX: Cross-Lingual Explanations of Idiomatic Expressions (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing definition generation systems are difficult to use in second language learning due to the presence of unfamiliar words and grammar. |
| Approach: | They propose to use cross-lingual explanations of idiomatic expressions to support vocabulary expansion for language learners. |
| Outcome: | The proposed system is able to explain idiomatic expressions in non-standard language. |
GMEG-EXP: A Dataset of Human- and LLM-Generated Explanations of Grammatical and Fluency Edits (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent work has explored the ability of large language models (LLMs) to generate explanations of existing labeled data. |
| Approach: | They propose a dataset to examine the ability of large language models to explain revisions in sentences by comparing human- and LLM-generated explanations of grammatical and fluency edits to a human evaluation criteria. |
| Outcome: | The proposed explanations address grammatical and fluency edits and are compared with a dataset built from the GMEG (Grammarly Multi-domain Evaluation for GEC) dataset. |
Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica (2021.emnlp-main)
Copied to clipboard
| Challenge: | Using pre-trained models, people use different styles to express their interpersonal goal and attitude in their communication. |
| Approach: | They use a dataset to collect lexicon usages across styles using two lenses: human perception and machine word importance. |
| Outcome: | The proposed model can predict human perception and machine word importance based on a popular style classifier like BERT . human- and machine-identified words share significant overlap for some styles . |
Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding (2021.acl-long)
Copied to clipboard
| Challenge: | a benchmark corpus of text in 15 different styles is used to study stylistic language . a similar benchmark is used for cross-style language understanding . |
| Approach: | They propose a benchmark corpus that combines existing datasets and collects a new one for cross-style language understanding. |
| Outcome: | The proposed benchmark corpus contains 15 different styles under four theoretical groupings: figurative, personal, affective, and interpersonal groups. |
Do Neural Language Models Show Preferences for Syntactic Formalisms? (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work on interpretability of deep neural language models concludes that many properties of natural language syntax are encoded in their representational spaces. |
| Approach: | They propose to examine whether syntactic structure adheres to a surface-syntactical or deep syntaktic style of analysis. |
| Outcome: | The proposed model prefers Universal Dependencies (UD) over Surface-Syntactic Universal Dependency (SUD) with interesting variations across languages and layers. |
Do Neural Language Models Inferentially Compose Concepts the Way Humans Can? (2024.lrec-main)
Copied to clipboard
| Challenge: | a new study shows that language models and humans may rely on different approaches to represent and compose lexical items across sentence structure. |
| Approach: | They propose to use a dataset to test the performance of neural language models and humans on inferentially driven conceptual compositions. |
| Outcome: | The proposed model elicits probability estimates for a noun in a minimally composed phrase . RoBERTa, BERT-large, and GPT-2 exhibited the closest resemblance to human responses . |
Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? (2020.acl-main)
Copied to clipboard
| Challenge: | a new study examines the impact of algorithmic explanations on simulatability of machine learning models . a model is simulatable when a person can predict its behavior on new inputs . |
| Approach: | They conduct human subject tests to isolate effect of algorithmic explanations on simulatability . they find ratings of explanations are not predictive of how helpful they are . |
| Outcome: | The results provide the first reliable estimates of how explanations influence simulatability . they show that ratings are not predictive of how helpful explanations are . |
Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent studies show that auto-encoders perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. |
| Approach: | They propose a discrete token-based perturbation approach to map "similar" sentences close by in latent space. |
| Outcome: | The proposed model can generate and perform language generation, style transfer and sentence interpolation tasks on unlabelled datasets in a zero-shot manner. |
Interpreting Style Representations via Style-Eliciting Prompts (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work has attempted to explain learning of style representations by generating natural language descriptions with large language models (LLMs) conditioned on input text. |
| Approach: | They propose a framework for interpreting style representations through style-eliciting prompts by prompting an LLM to generate text conditioned on these features. |
| Outcome: | The proposed framework outperforms baselines that directly prompt LLMs with target text, and achieves superior performance in both style description and style imitation. |