mlsanityData to 14 Oct 2026

An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis

arXiv 2608.07439 ↗First posted 7 Aug 2026cs.CL quant-phcited by 0

Not on the map. Why?

Abstract (arXiv)

Quantum natural language processing (QNLP) provides a grammar-aware framework for text modeling, and Distributional Compositional Categorical (DisCoCat) is one of its theoretically grounded formulations. Prior work on financial sentiment analysis has identified practical limitations of DisCoCat, including parser sensitivity, high simulation cost, and difficulty handling longer sentences. We study an LLM-assisted preprocessing workflow that uses controlled rewriting to compress, simplify, or decompose moderate-complexity financial sentiment sentences into parser-compatible, circuit-efficient variants while preserving sentiment-bearing meaning. We compare prompting strategies, language models, and filtering configurations with the low-complexity-only DisCoCat baseline of Stein et al. At the circuit level, the strongest compression variants reduce average qubit and gate counts by more than 70 percent relative to the raw moderate-complexity subset. Across repeated training runs, GPT-4.1-mini with Prompt B achieves the highest observed mean accuracy, 0.550 ± 0.035, compared with 0.521 ± 0.050 for the baseline. Larger training splits do not necessarily improve downstream performance; across evaluated configurations, training-split size has a moderately negative association with accuracy (Pearson r=-0.446). These results provide exploratory evidence that LLM-assisted rewriting can make some moderate-complexity inputs usable within the evaluated DisCoCat configuration, while highlighting prompt design, filtering, and circuit-aware preprocessing as considerations for more scalable QNLP-based financial sentiment analysis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 39 references that are in the map. First posted on arXiv 7 Aug 2026.

Builds on

18 of 39 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  4. 2021Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LMcited by 632
  5. 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 385
  6. 2021Generalization in quantum machine learning from few training datacited by 216
  7. 2020Quantum Long Short-Term Memorycited by 120
  8. 2021QNLP in Practice: Running Compositional Models of Meaning on a Quantum Computercited by 67
  9. 2021The Dawn of Quantum Natural Language Processingcited by 61
  10. 2024Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inferencecited by 53
  11. 2023Extending Context Window of Large Language Models via Semantic Compressioncited by 45
  12. 2020Quantum Natural Language Processing on Near-Term Quantum Computerscited by 39
6 more
  1. 2023Applying QNLP to sentiment analysis in financecited by 23
  2. 2023Semantic Compression With Large Language Modelscited by 17
  3. 2025Redefining Simplicity: Benchmarking Large Language Models from Lexical to Document Simplificationcited by 6
  4. 2024InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Modelscited by 4
  5. 2025LLM-based Text Simplification and its Effect on User Comprehension and Cognitive Loadcited by 4
  6. 2022A multiclass Q-NLP sentiment analysis experiment using DisCoCatcited by 2

Built on by

Not cited yet.