Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2511.20409

NormEval: A Unified Multi-Metric Framework for Evaluating Semantic Fidelity in Text Normalization

Md Abdullah Al Kafi·Raka Moni·Walayat Hussain
View original source ↗Read source document ↗Export metadata ↓

Abstract

Text normalization methods such as stemming and lemmatization are fundamental components of NLP pipelines. As new normalization tools are developed for diverse languages, evaluation methodologies remain fragmented, relying on Compression Ratio, downstream accuracy, or sequence-to-sequence prediction scores in isolation, failing to distinguish between beneficial vocabulary reduction and harmful semantic distortion. Moreover, text normalization underpins intelligent systems in high-stakes domains, including clinical decision support and legal document analysis, and principled evaluation methodology is essential. This paper proposes NormEval, a unified, multilingual evaluation framework comprising five complementary metrics: Compression Ratio (CR), Model Performance Delta (MPD), Information Retention Score (IRS), Algorithm Effectiveness Score (AES), and Average Normalized Levenshtein Distance (ANLD). These metrics assess normalization quality across three dimensions: macro-level efficiency, downstream utility, and micro-level morphological fidelity. The framework operationalizes a Safety Gate hypothesis: ANLD functions as an intrinsic structural hygiene check, utilizing character-level divergence ($Δ$) to reveal aggressive mutations that macro-level embeddings and downstream tasks mask. Comprehensive ablation experiments on both Bangla and English datasets show that all the components are indispensable, and that the removal of any individual metric leads to a decrease in at least one evaluation aspect, which ultimately results in misleading algorithm rankings.

Explore related subjects

cs.CL

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Md Abdullah Al Kafi, Raka Moni, Walayat Hussain. 2026-05-29. NormEval: A Unified Multi-Metric Framework for Evaluating Semantic Fidelity in Text Normalization. https://arxiv.org/abs/2511.20409

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

DA-Cramming: Enhancing Cost-Effective Language Model Pretraining with Dependency Agreement Integration

Pretraining language models is still a challenge for many researchers due to its substantial computational costs. As such, there is growing interest in developing more affordable pretraining methods. One notable advancement in this area is the Cramming technique (Geiping and Goldstein, 2022), which enables the pretraining of BERT-style language models using just one GPU in a single day. Building on this innovative approach, we introduce the Dependency Agreement Cramming (DA-Cramming), an efficient framework that integrates information about dependency agreements into the pretraining process. Unlike existing methods that leverage similar semantic information during finetuning, our approach represents a pioneering effort focusing on enhancing the foundational language understanding with semantic information during pretraining. We meticulously design a dual-stage pretraining work flow with four dedicated submodels to capture representative dependency agreements at the chunk level, effectively transforming these agreements into embeddings to benefit the pretraining. Extensive empirical results demonstrate that our method significantly outperforms previous methods across various tasks.

cs.CL↗
arXiv2026

BigO(Bench): Can LLMs Generate Code with Controlled Time and Space Complexity?

We introduce BigO(Bench), a novel coding benchmark designed to evaluate the capabilities of generative language models in understanding and generating code with specified time and space complexities. This benchmark addresses the gap in current evaluations that often overlook the ability of models to comprehend and produce code constrained by computational complexity. BigO(Bench) includes tooling to infer the algorithmic complexity of any Python function from profiling measurements, including human- or LLM-generated solutions. BigO(Bench) also includes of set of 3,105 coding problems and 1,190,250 solutions from Code Contests annotated with inferred (synthetic) time and space complexity labels from the complexity framework, as well as corresponding runtime and memory footprint values for a large set of input sizes. We present results from evaluating multiple state-of-the-art language models on this benchmark, highlighting their strengths and weaknesses in handling complexity requirements. In particular, token-space reasoning models are unrivaled in code generation but not in complexity understanding, hinting that they may not generalize well to tasks for which no reward was given at training time.

cs.CL↗
arXiv2026

UR$^2$: Unify RAG and Reasoning through Reinforcement Learning

Large Language Models (LLMs) have shown strong capabilities through two complementary paradigms: Retrieval-Augmented Generation (RAG) for knowledge grounding and Reinforcement Learning from Verifiable Rewards (RLVR) for complex reasoning. However, existing attempts to unify these paradigms remain narrow in scope, typically limited to open-domain QA with fixed retrieval settings, which constrains generalization to broader domains. To address this limitation, we propose UR$^2$ (Unified RAG and Reasoning)), a general reinforcement learning framework that dynamically coordinates retrieval and reasoning. UR$^2$ introduces two key designs: a difficulty-aware curriculum that selectively invokes retrieval only for challenging instances, and a hybrid knowledge access strategy that combines domain-specific offline corpora with on-the-fly LLM-generated summaries. Together, these components mitigate the imbalance between retrieval and reasoning and improve robustness to noisy information. Experiments on open-domain QA, MMLU-Pro, medical, and mathematical reasoning tasks show that UR$^2$, built on Qwen-2.5-3/7B and LLaMA-3.1-8B, consistently outperforms existing RAG and RL baselines, and achieves performance comparable to GPT-4o-mini and GPT-4.1-mini on several benchmarks. Code, models, and data are available at https://github.com/Tsinghua-dhy/UR2.

cs.CL↗