CharBench: Evaluating the Role of Tokenization in Character-Level Tasks

• URL: http://arxiv.org/abs/2508.02591v2
• Date: Wed, 06 Aug 2025 09:06:34 GMT
• Title: CharBench: Evaluating the Role of Tokenization in Character-Level Tasks
• Authors: Omri Uzan, Yuval Pinter,
• Abstract summary: CharBench is a benchmark of character-level tasks that is two orders of magnitude larger than existing alternatives.<n>We present an analysis of how intrinsic properties of words and their segmentations into tokens correspond to model performance.<n>For counting tasks, we find that tokenization properties are weakly correlated with correctness, while the length of the queried word and the actual character count play a more significant part.
• Score: 3.937454839700144
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tasks that require character-level reasoning, such as counting or locating characters within words, remain challenging for contemporary language models. A common conjecture is that language models' reliance on subword units, rather than characters, contributes to their struggles with character-level tasks, yet recent studies offer conflicting conclusions about the role of tokenization, leaving its impact unclear. To address this gap, we introduce CharBench, a comprehensive benchmark of character-level tasks that is two orders of magnitude larger than existing alternatives. We evaluate a diverse range of leading open-weight and proprietary models on CharBench and find that it presents a significant challenge to modern LLMs, with an average accuracy of 43.6% and 32.3% on some tasks. We present an in-depth analysis of how intrinsic properties of words and their segmentations into tokens correspond to model performance. For counting tasks, we find that tokenization properties are weakly correlated with correctness, while the length of the queried word and the actual character count play a more significant part. In contrast, for tasks requiring intra-word positional understanding, performance is negatively correlated with the length of the token containing the queried character, suggesting that longer tokens obscure character position information for LLMs. We encourage future work to build on the benchmark and evaluation methodology introduced here as tools for improving model performance on such tasks.

Related papers

• TASE: Token Awareness and Structured Evaluation for Multilingual Language Models [8.058965963418785]
  TASE is a benchmark designed to evaluate large language models' ability to perceive and reason about token-level information.<n> TASE covers 10 tasks under two core categories: token awareness and structural understanding, spanning Chinese, English, and Korean.<n>We evaluate over 30 leading commercial and open-source LLMs, including O3, Claude 4, Gemini 2.5 Pro, and DeepSeek-R1.
  arXiv  Detail & Related papers  (2025-08-07T15:11:17Z)
• Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations [83.93566096400723]
  We find that instruction-tuned models retain up to 93.4% of their original performance when given a randomly sampled tokenization.<n>Character-level segmentation improves string manipulation and code understanding tasks by up to +14%.<n>Right-aligned digit grouping enhances large-number arithmetic by +33%.
  arXiv  Detail & Related papers  (2025-06-23T18:02:26Z)
• Tokenization is Sensitive to Language Variation [14.568179478275255]
  Tokenizers split texts into smaller units and might behave differently for less common linguistic forms.<n>This might affect downstream LLM performance differently on two types of tasks.<n>We find that the best tokenizer varies on the two task types and that the pre-tokenizer has the biggest overall impact on performance.
  arXiv  Detail & Related papers  (2025-02-21T09:58:54Z)
• Enhancing LLM Character-Level Manipulation via Divide and Conquer [74.55804812450164]
  Large Language Models (LLMs) have demonstrated strong generalization capabilities across a wide range of natural language processing (NLP) tasks.<n>They exhibit notable weaknesses in character-level string manipulation, struggling with fundamental operations such as character deletion, insertion, and substitution.<n>We propose Character-Level Manipulation via Divide and Conquer, a novel approach designed to bridge the gap between token-level processing and character-level manipulation.
  arXiv  Detail & Related papers  (2025-02-12T07:37:39Z)
• STAB: Speech Tokenizer Assessment Benchmark [57.45234921100835]
  Representing speech as discrete tokens provides a framework for transforming speech into a format that closely resembles text. We present STAB (Speech Tokenizer Assessment Benchmark), a systematic evaluation framework designed to assess speech tokenizers comprehensively. We evaluate the STAB metrics and correlate this with downstream task performance across a range of speech tasks and tokenizer choices.
  arXiv  Detail & Related papers  (2024-09-04T02:20:59Z)
• TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models [12.143152327874802]
  Large Language Models (LLMs) excel in code-related tasks like code generation, but benchmark evaluations often overlook task characteristics, such as difficulty.<n>This paper introduces a framework using diverse prompts and Item Response Theory (IRT) to efficiently assess LLMs' capabilities and benchmark task characteristics.
  arXiv  Detail & Related papers  (2024-07-30T22:31:19Z)
• Identifying and Analyzing Performance-Critical Tokens in Large Language Models [52.404072802235234]
  We study how large language models learn to perform tasks from demonstrations.<n>Our work sheds light on how large language models learn to perform tasks from demonstrations and deepens our understanding of the roles different types of tokens play in large language models.
  arXiv  Detail & Related papers  (2024-01-20T20:55:21Z)
• SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks [88.4408774253634]
  Spoken language understanding (SLU) tasks have been studied for many decades in the speech research community. There are not nearly as many SLU task benchmarks, and many of the existing ones use data that is not freely available to all researchers. Recent work has begun to introduce such benchmark for several tasks.
  arXiv  Detail & Related papers  (2022-12-20T18:39:59Z)
• Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training [36.19870483966741]
  We develop a causal intervention framework to learn robust and interpretable character representations inside subword-based language models. Our method treats each character as a typed variable in a causal model and learns such causal structures. We additionally introduce a suite of character-level tasks that systematically vary in their dependence on meaning and sequence-level context.
  arXiv  Detail & Related papers  (2022-12-19T22:37:46Z)
• Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extraction [80.38130122127882]
  We introduce 14 probing tasks targeting linguistic properties relevant to neural relation extraction (RE) We use them to study representations learned by more than 40 different encoder architecture and linguistic feature combinations trained on two datasets. We find that the bias induced by the architecture and the inclusion of linguistic features are clearly expressed in the probing task performance.
  arXiv  Detail & Related papers  (2020-04-17T09:17:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.