arXiv Computation and Language November 4, 2026 By Artem Suslov, Takehiro Hashimoto

Distilling Literary Sentiment from LLM Annotations into an Ordinal BERT Model

Read the original on arXiv Computation and Language →

The paper explores using LLM-generated annotations to train smaller BERT models for literary sentiment analysis. Five BERT variants were fine‑tuned with ordinal regression on 10,889 sentences labeled by Gemma 4 31B on a ten‑point scale, and evaluated on 1,923 human‑annotated sentences from Hemingway’s *The Old Man and the Sea*. BERT‑large achieved a Kendall’s τ of 0.589, close to the teacher’s 0.604, and BERT‑base outperformed the teacher on non‑neutral sentences with an MAE of 0.726 versus 1.116.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jun 30

Do We Still Need Fine Tuning? Turkish Sentiment Analysis in the Era of Large Language Model

arXiv:2606. 29614v1 Announce Type: cross Abstract: This study examines whether supervised fine-tuning remains necessary for Turkish sentiment analysis in the era of large language models.

By Sercan Karaka\c{s}, Yusuf \c{S}im\c{s}ek

llms nlp fine-tuning

arXiv Computation and Language

Oct 19

Who Do Perspectivist Models Predict Well? Annotator Agreement, Sparsity, and Performance

The paper investigates how perspectivist NLP models perform when predicting annotations from different annotators, focusing on those who diverge from the majority or provide fewer annotations. It compiles the largest set of perspectivist datasets with ordinal labels and evaluates various algorithms across them. The study finds that models tend to perform better on annotators who agree with others, while the rate at which annotators provide responses does not significantly affect performance.

By London Lowmanstone IV, Vaagishwaran Sivakumar, Anwesha Samaddar, Akul Mundada, Harnoor Kaur, Maria Gini

nlp efficiency

arXiv AI

Jun 18

As Easy as Rocket Science: Assessing the Ability of Large Language Models to Interpret Negation in Figurative Language

arXiv:2606. 18922v1 Announce Type: cross Abstract: Figurative language and negation are two areas that challenge current language models, however, both are widely used throughout written and spoken language.

By Jasmine Owers, Edwin Simpson, Martha Lewis

llms

arXiv Machine Learning

4d ago

Enhancing Sentiment Classification on Small Datasets through Data Augmentation and Transfer Learning

The paper investigates how data augmentation can improve sentiment classification on small datasets. Three augmentation techniques—Easy Data Augmentation (EDA), back‑translation, and contextual token substitution—are evaluated with both traditional classifiers (Logistic Regression, Random Forest) and BERT. Results show that all methods boost performance, with contextual augmentation best for BERT and EDA/back‑translation benefiting traditional models.

By Mahmoud S. Mayaleh, Samer A. Mayaleh

llms fine-tuning

Hugging Face Trending Papers

Jul 13

A Durability and Cross-Language Transfer Benchmark for a Validated Teaching-Feedback Classification Protocol

Institutions collect far more open-ended teaching-evaluation feedback than they read. A prior study introduced a validated protocol for classifying such comments by thematic category and sentiment, built from a documented annotation guide, an intra-annotator reliability measurement, stratified cross-validation, and a held-out evaluation on a Spanish institutional corpus with a frozen-encoder design.

llms rag benchmarks

arXiv Computation and Language

Sep 30

Concept Direction Reliability Across Languages with Different Tokenizer Fertility

arXiv:2609.36194v1 Announce Type: new Abstract: Extracted sentiment directions can vary across samples even when downstream sentiment classification remains accurate. To evaluate direction reproducib...

By Muhammad Abdullahi Said, Abass Oguntade, Elisha Komolafe, Babangida Sani, Fatima Muhammad Adam, Muhammad Sammani Sani

llms nlp