Image de couverture de livre

When Informal Text Breaks NLI: Tokenization Failure, Distribution Shift, and Targeted Mitigations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Aluguvelly, Avinash Goutham
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing
par: Negru, Vlad Andrei, et autres
Publié: (2025)

ViLegalNLI: Natural Language Inference for Vietnamese Legal Texts
par: Duong, Nhung Thi-Hong, et autres
Publié: (2026)

Mitigating Spurious Correlations in NLI via LLM-Synthesized Counterfactuals and Dynamic Balanced Sampling
par: Jaimes, Christopher Román
Publié: (2025)

PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise
par: Harary, Sapir, et autres
Publié: (2025)

XNLIeu: a dataset for cross-lingual NLI in Basque
par: Heredia, Maite, et autres
Publié: (2024)

Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
par: Quan, Xin, et autres
Publié: (2025)

Affective-NLI: Towards Accurate and Interpretable Personality Recognition in Conversation
par: Wen, Zhiyuan, et autres
Publié: (2024)

The Art of Breaking Words: Rethinking Multilingual Tokenizer Design
par: Thakur, Aamod, et autres
Publié: (2025)

Sarang at DEFACTIFY 4.0: Detecting AI-Generated Text Using Noised Data and an Ensemble of DeBERTa Models
par: Trivedi, Avinash, et autres
Publié: (2025)

NL-Eye: Abductive NLI for Images
par: Ventura, Mor, et autres
Publié: (2024)

Cognitive-Mental-LLM: Evaluating Reasoning in Large Language Models for Mental Health Prediction via Online Text
par: Patil, Avinash, et autres
Publié: (2025)

READ: Reinforcement-based Adversarial Learning for Text Classification with Limited Labeled Data
par: Sharma, Rohit, et autres
Publié: (2025)

Data-efficient Targeted Token-level Preference Optimization for LLM-based Text-to-Speech
par: Kotoge, Rikuto, et autres
Publié: (2025)

Text Classification Under Class Distribution Shift: A Survey
par: Costache, Adriana Valentina, et autres
Publié: (2025)

First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI
par: Banerjee, Sourav, et autres
Publié: (2024)

Say Anything but This: When Tokenizer Betrays Reasoning in LLMs
par: Ayoobi, Navid, et autres
Publié: (2026)

Revisiting NLI: Towards Cost-Effective and Human-Aligned Metrics for Evaluating LLMs in Question Answering
par: Balamurali, Sai Shridhar, et autres
Publié: (2025)

Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction
par: Yuan, Mengying, et autres
Publié: (2025)

HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention
par: Goswami, Saumya, et autres
Publié: (2025)

S$^2$-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency
par: Zeng, Yuting, et autres
Publié: (2025)

Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling
par: Yu, Yao-Ching, et autres
Publié: (2024)

TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
par: Fu, Lucheng, et autres
Publié: (2026)

Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
par: Meng, Haoming, et autres
Publié: (2026)

Text Generation Beyond Discrete Token Sampling
par: Zhuang, Yufan, et autres
Publié: (2025)

Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Diffusion Language Models
par: Yao, Lin
Publié: (2026)

Support-Contra Asymmetry in LLM Explanations
par: Patil, Avinash
Publié: (2025)

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
par: Sun, Zhongxiang, et autres
Publié: (2026)

Thunder-Tok: Minimizing Tokens per Word in Tokenizing Korean Texts for Generative Language Models
par: Cho, Gyeongje, et autres
Publié: (2025)

Token Masking Improves Transformer-Based Text Classification
par: Xu, Xianglong, et autres
Publié: (2025)

Explainability-Based Token Replacement on LLM-Generated Text
par: Mohammadi, Hadi, et autres
Publié: (2025)

Training Text-to-Molecule Models with Context-Aware Tokenization
par: Kim, Seojin, et autres
Publié: (2025)

FZI-WIM at SemEval-2024 Task 2: Self-Consistent CoT for Complex NLI in Biomedical Domain
par: Liu, Jin, et autres
Publié: (2024)

Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish
par: Philippy, Fred, et autres
Publié: (2024)

Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review
par: Yu, Sungduk, et autres
Publié: (2025)

Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review
par: Yu, Sungduk, et autres
Publié: (2024)

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN
par: Xu, Yao, et autres
Publié: (2025)

Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs
par: Li, Yanhong, et autres
Publié: (2025)

Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models
par: Arakelyan, Erik, et autres
Publié: (2024)

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling
par: Yun, Heecheol, et autres
Publié: (2025)

Breaking the Silence: A Dataset and Benchmark for Bangla Text-to-Gloss Translation
par: Abdullah, Sharif Mohammad, et autres
Publié: (2025)