---
title: "Distilling Literary Sentiment from LLM Annotations into an Ordinal BERT Model"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.02985v1"
permalink: "https://feed.astralor.com/items/itm_3cb377b29cb1b96f9d532fb6"
published: "2026-11-02T11:56:12.000Z"
score: 56
channel: "ai"
tags: ["LLM","多模态","Distilling Literary Sentiment","LLM Annotations","Ordinal BERT Model","LLM-generated"]
---

# Distilling Literary Sentiment from LLM Annotations into an Ordinal BERT Model

## 速览

The scarcity of human-annotated literary corpora limits the development of domain-specific sentiment analysis models. This study investigates whether LLM-generated annotations can supervise smaller models for literary s…

## 关键点

- The scarcity of human-annotated literary corpora limits the development of domain-specific sentiment analysis models.
- This study investigates whether LLM-generated annotations can supervise smaller models for literary sentiment analysis.
- We fine-tune five BERT models using ordinal regression on 10,889 literary sentences annotated by Gemma 4 31B on a ten-point sentiment scale.

## 全文

The scarcity of human-annotated literary corpora limits the development of domain-specific sentiment analysis models. This study investigates whether LLM-generated annotations can supervise smaller models for literary sentiment analysis. We fine-tune five BERT models using ordinal regression on 10,889 literary sentences annotated by Gemma 4 31B on a ten-point sentiment scale. The models are evaluated against 1,923 human-annotated sentences from Hemingway's "The Old Man and the Sea", alongside the teacher model and conventional baselines. BERT-large achieves a Kendall's $τ$ of 0.589, approaching the teacher's 0.604. Although a constant-neutral predictor achieves the lowest overall mean absolute error (MAE), BERT-base outperforms the teacher on non-neutral sentences, achieving an MAE of 0.726 versus 1.116. These findings demonstrate the potential of LLM-generated supervision for developing smaller literary sentiment models, while highlighting the limitations of aggregate error metrics on predominantly neutral datasets.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_3cb377b29cb1b96f9d532fb6