ACL ARR 2025 May Submissions

An Evaluation Resource for Grounding Translation Errors
ACL ARR 2025 May Submission7529 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders
ACL ARR 2025 May Submission7523 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Promptception: How Sensitive Are Large Multimodal Models to Prompts?
ACL ARR 2025 May Submission7522 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments
ACL ARR 2025 May Submission7519 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
RD-MCSA: A Multi-Class Sentiment Analysis Approach Integrating In-Context Classification Rationales and Demonstrations
ACL ARR 2025 May Submission7518 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Diagnosis of Dysarthria Severity and Explanation Generation Using XAI-Enhanced CLINIC-GENIE on Diadochokinetic Tasks
ACL ARR 2025 May Submission7514 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Exploring the Impact of Personality Traits on LLM-based Conversational Recommender Systems
ACL ARR 2025 May Submission7509 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Length-Controlled Margin-Based Preference Optimization without Reference Model
ACL ARR 2025 May Submission7507 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Learning SQL Like a Human: Structure-Aware Curriculum Learning for Text-to-SQL Generation
ACL ARR 2025 May Submission7506 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents
ACL ARR 2025 May Submission7505 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Prioritizing Financially Informative Comments via Group Relative Policy Optimization
ACL ARR 2025 May Submission7503 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
ACL ARR 2025 May Submission7496 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
ACL ARR 2025 May Submission7489 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
The Impact of Language Mixing on Bilingual LLM Reasoning
ACL ARR 2025 May Submission7479 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMs
ACL ARR 2025 May Submission7478 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Natural Context Drift Undermines the Natural Language Understanding of Large Language Models
ACL ARR 2025 May Submission7477 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
CHEF: A Comparative Hallucination Evaluation Framework for Large Language Models
ACL ARR 2025 May Submission7468 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Weaver : Interweaving SQL and LLM for Table Reasoning
ACL ARR 2025 May Submission7463 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Pre-trained Models Perform the Best When Token Distributions Follow Zipf’s Law
ACL ARR 2025 May Submission7460 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
XLQA: A Benchmark for Locale-Aware Multilingual Open-Domain Question Answering
ACL ARR 2025 May Submission7448 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Order Doesn't Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation
ACL ARR 2025 May Submission7445 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
SOTOPIA-RL: Reward Design for Social Intelligence
ACL ARR 2025 May Submission7444 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Entropy-Based Dynamic Hybrid Retrieval for Adaptive Query Weighting in RAG Pipelines
ACL ARR 2025 May Submission7430 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
South AsianVoices in LLMs: Culturally Aware Multilingual Instruction Fine-Tuning for South Asian Low-Resource Languages
ACL ARR 2025 May Submission7429 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
RoadscapesQA: A Multitask, Multimodal Dataset for Visual Question Answering on Indian Roads
ACL ARR 2025 May Submission7423 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone