ACL 2026 — Machine Translation & Multilingual

Machine Translation & Multilingual

112 papers Links not yet available — ACL proceedings pending on ACL Anthology.

Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation
CLEAR: Cross-Lingual Enhancement in Retrieval via Reverse-training
SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification
Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech
MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation
EMCEE: Improving Multilingual Capability of LLMs via Bridging Knowledge and Reasoning with Extracted Synthetic Multilingual Context
TRACE: Evaluating Execution Efficiency of LLM-Based Code Translation
One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers
LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Models
Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation
Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation
What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation
DeReA: Improving Idiom Translation with Detect-Retrieve-Arbitrate Reasoning
All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG
Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization
NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning
DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation
Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning
VFA: Empoweing Multilingual MLLMs via Vision-Free Adaptation
Think in Latent Thoughts: A New Paradigm for Gloss-Free Sign Language Translation
MT³: A Synergistic Multi-Task RL Framework for Specializing MLLMs in Text Image Machine Translation
M²PO: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation
Losing our Tail, Again: (Un)Natural Selection & Multilingual LLMs
Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages
Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AI
LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs
Evaluating the Impact of Verbal Multiword Expressions on Machine Translation
HAT: Hallucination Annotation for Translation
Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors
ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application
Lost in Translation, and Found: Detecting and Interpreting Translation Effects
Paraphrasing as Zero-shot Translation with Feature-guided Diversity Enhancement
XToM: Exploring the Multilingual Theory of Mind for Large Language Models
TAMA: Target-Aware Multilingual Abuse Detection by Cascaded Conditional Multi-Task Learning
GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL
MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis
Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning
Language on Demand, Knowledge at Core: Composing LLMs with Encoder-Decoder Translation Models for Extensible Multilinguality
SAME: Signer-Aware Mixture-of-Experts for Test-Time Adaptation in Sign Language Translation
The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation
How Can Synthetic Data Improve Multilingual Language Model Pretraining? A Data Quality Perspective
Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages
IRIS: Interleaved Reinforcement with Incremental Staged Curriculum for Cross-Lingual Mathematical Reasoning
Right at My Level: A Unified Multilingual Framework for Proficiency-Aware Text Simplification
Knowledge Beyond Language: Bridging the Gap in Multilingual Machine Unlearning Evaluation
Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
Revisiting Metric Reliability for Fine-grained Evaluation of Machine Translation and Summarization in Indian Languages
LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAMΔ Integration into Upcycled MoE
Improving Long-Context Translation via Self-Supervised Dual Learning
Multilingual and Cross-Lingual Citation Needed Detection on Wikipedia for Lower-Resource Languages
Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs
TOWER+: Bridging Generality and Translation Specialization in Multilingual LLMs
Culture-Aware Machine Translation in Large Language Models: Benchmarking and Investigation
GOLEMcoref: A Multilingual Coreference Dataset of Fiction
How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP
MPR-GUI: Benchmarking and Enhancing Multilingual Perception and Reasoning in GUI Agents
Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework
Beyond Atomic Characters: Glyph-Aware Sub-character Alignment for Low-Resource Multilingual OCR
Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation
CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning
An Experimental Study on the Influence of Culture on Cross-Lingual Sentiment Transfer
SwissGov-RSD: A Human-annotated, Cross-lingual Benchmark for Token-level Recognition of Semantic Differences Between Related Documents
When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval
Alexandria: A Multi-Domain Dialectal Arabic Machine Translation Dataset for Culturally Inclusive and Linguistically Diverse LLMs
Vocabulary Shapes Cross-Lingual Variation of Word-Order Learnability in Language Models
MQM Re-Annotation: A Technique for Collaborative Evaluation of Machine Translation
Multilingual Language Models Encode Script Over Linguistic Structure
ChiKhaPo: A Large-Scale Multilingual Benchmark for Evaluating Lexical Comprehension and Generation in Large Language Models
Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation
MMSciCode: Real-world Evaluation of Multilingual Multi-Discipline Scientific Research Coding
Where the Cat Sat: A Multilingual Framework for Spatial Language Understanding
LCMA-SRT: Language-Conditional Mixture-of-Experts Adapters for Joint Multilingual Speech Recognition and Translation
Massively Multilingual Joint Segmentation and Glossing
Bootstrapping Code Translation with Weighted Multilanguage Exploration
LangSAE Editing: Improving Multilingual Information Retrieval via Post-hoc Language Identity Removal
Framing Political Bias in Multilingual LLMs Across Pakistani Languages
Mitigating Tokenization-Induced Distance Distortion in Long-Context Multilingual Machine Translation
The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining
FairQE: Multi-Agent Framework for Mitigating Gender Bias in Translation Quality Estimation
AdaDPI: Document-level Translation Adaptive Agent via Dynamic Parametric Internalization
DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection
G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment
Towards Fast and Accurate Modeling for Cross-Lingual Label Projection
False Friends or Cognates? A Cross-lingual Semantic Ambiguity Evaluation for Galician, Portuguese and Spanish
Phonemes to the Rescue: Multilingual Tokenization Based on International Phonetic Alphabet
DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis
One Pair Suffices: Unlocking Universal Zero-Shot Translation via Cross-Architecture Alignment
Quantifying the Impact of Translation Errors on Multilingual LLM Evaluation
Prosody as Supervision: Bridging the Non-Verbal–Verbal for Multilingual Speech Emotion Recognition
Measuring User’s Mental Models of Speech Translation in Human-AI Collaboration
PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation
LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models
POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering
CLAOCS-TX: Cross-Lingual Triplet Extraction with Aspect-Opinion-Aware Code-Switched Prompting and LLM-Guided Contrastive Distillation
When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models
A Shared Geometry of Difficulty in Multilingual Language Models
Authorship Attribution in Multilingual Machine-Generated Texts
Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction
Selective Contrastive Learning For Gloss Free Sign Language Translation
Mind the Pause: Disfluency-Aware Objective Tuning for Multilingual Speech Correction with LLMs
MUTANT: A Recipe for Multilingual Tokenizer Design
Characterizing and Evaluating Working Emotion Vocabularies in Multilingual Large Language Models
Toward Robust Evaluation for Multilingual Grammatical Error Correction: Can Large Language Models Replace Human References?
A Multilingual Social Bias Benchmark Incorporating Thinking Processes
Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling
Typology-Aware Multilingual Morphosyntactic Parsing with Joint Abstract Node Modeling