cs.CLNov 2, 2026

Finding Errors Is Not Enough: Selective Model Escalation for Entity-Targeted Sentiment Analysis

Authors: Nishan Chatterjee, Matthew Purver, Antoine Doucet, Senja Pollak

Organizations: Jožef Stefan Institute, Ljubljana, Slovenia · Jožef Stefan International Postgraduate School, Ljubljana, Slovenia · University of La Rochelle, La Rochelle, France · Queen Mary University of London, London, United Kingdom · 

Abstract

Improving a sentiment classifier with limited resources involves more than simply deciding how much data to collect or which model to train. A labelled collection may lack examples of an important class. Once trained, a classifier may benefit from another model even when that model is weaker on its own. We study these decisions in document-level Entity-Level Sentiment Analysis (ELSA), primarily using South Slavic news. We first compare acquisition orders as collections grow. We then use uncertainty to choose which predictions to revisit, how many to process, and whether an alternative encoder or local LLM can correct them. Finally, we select complete routing policies on development data for held-out evaluation. Minority-prioritised acquisition helps at some very small training sizes, but not consistently thereafter. On SentiCoref, an oracle correcting all errors in the least-confident 10% without harming correct predictions would add 9.14 Macro-F1 points; however the best evaluated action gains only 0.90. Encoder averaging helps on AspectBench and NewsMTSC but harms SentiCoref, where selective LLM assistance is more promising. Both development-selected policies route 30% of records to the encoder-assisted LLM, yielding observed gains of 1.02 points on SentiCoref (interval includes zero) and 1.71 on NewsMTSC, at substantially different inference costs.

Figures & tables

Appendix figures & tables30 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Mar 8, 2026

QuadAI at SemEval-2026 Task 3: Ensemble Learning of Hybrid RoBERTa and LLMs for Dimensional Aspect-Based Sentiment Analysis

We present our system for SemEval-2026 Task 3 on dimensional aspect-based sentiment regression. Our approach combines a hybrid RoBERTa encoder, which jointly predicts sentiment using regression and discretized classification heads, with large language models (LLMs) via prediction-level ensemble learning. The hybrid encoder improves prediction stability by combining continuous and discretized sentiment representations. We further explore in-context learning with LLMs and ridge-regression stacking to combine encoder and LLM predictions. Experimental results on the development set show that ensemble learning significantly improves performance over individual models, achieving substantial reductions in RMSE and improvements in correlation scores. Our findings demonstrate the complementary strengths of encoder-based and LLM-based approaches for dimensional sentiment analysis. Our development code and resources will be shared at https://github.com/aaronlifenghan/ABSentiment
Oct 5, 2026

Evaluating Escalation Signals for LLM Routing: Targets, Controls, and Five Ways to Fool Yourself

Deciding when to escalate a query from a small language model to a larger one requires a cheap signal that predicts, before the large model is called, whether escalating would help. Semantic entropy, originally developed to detect hallucinations, is a natural candidate: it measures how much a model's sampled answers disagree in meaning, and high disagreement often signals an unreliable answer. We test it across three benchmarks and two model families. On GSM8K, with a small/large pair about twelve times apart in size, semantic entropy reliably distinguishes the small model's mistakes (AUROC 0.871) and improves routed accuracy over random escalation by up to nine points at matched cost. An earlier strong-looking result on a synthetic benchmark proved misleading: a simple rule based only on question difficulty, with no model involved, matched semantic entropy almost exactly. This paper's main contribution is a set of checks that catch this before it is reported as real. We show that scoring a cheap, question-only difficulty estimate alongside any signal reveals whether the signal adds real information or just tracks how hard a question looks; that two reasonable definitions of "escalation worked" can produce very different results on the same data; that a benchmark can leave almost no room for any signal to beat simply always using the large model; and that the true cost of live sampling can make routing more expensive than calling the large model directly. For a cheaper alternative that reuses cached past outcomes, we show how to predict whether it will work on a new dataset -- confirmed by correctly forecasting a collapse from AUROC 0.908 to chance level (0.518) ahead of time. We offer these as a general checklist for evaluating escalation signals.
Aug 15, 2026

When AI Rewrites, Classifiers Relax: Uncertainty-Aware Sentiment Analysis on Sarcastic and AI-Paraphrased Social Text

Sentiment classifiers are increasingly applied to social media content that is either sarcastic or AI-generated --- two distributional regimes where standard evaluations offer little guidance. We present a three-part empirical study of sentiment classifier behaviour under these conditions. First, we find that confidence scores on sarcastic text are significantly lower than on non-sarcastic text (Mann--Whitney p=2×10−6p = 2 \times 10^{-6}), confirming that classifiers sense their own uncertainty on ironic content even without explicit uncertainty modelling. Second, and counterintuitively, we show that sentiment classifiers achieve higher accuracy on AI-paraphrased reviews than on the original human-authored text (RoBERTa: +5.8+5.8 pp for Qwen3.5-4B paraphrases, +3.7+3.7 pp for Gemma4-E4B), revealing a cross-domain stylistic alignment effect: AI paraphrases remove distributional noise that confounds Twitter-trained classifiers, producing cleaner, more prototypical sentiment text. Third, we demonstrate that a lightweight abstention wrapper --- flagging the 14%14\% of inputs with confidence below 0.60.6 --- improves accuracy from 82.2% to 88.9% (+6.7+6.7 pp) on the retained set. We further compare Semantic Entropy and MC-Dropout-style disagreement as uncertainty signals and find near-identical AUROC (0.6500.650 vs.\ 0.6460.646) on sarcastic text, suggesting that for short social media inputs, both methods are interchangeable. Our results motivate a shift from confident single-label prediction to uncertainty-aware abstention in high-stakes sentiment applications such as mental health flagging and content moderation.