ACL ARR 2025 May Submissions

Think Twice, Generate Once: Enhancing LLMs Safety via Progressive Self-Reflection
ACL ARR 2025 May Submission7167 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
ReSLT: Retrieval-enhanced Sign Language Translation with LLMs
ACL ARR 2025 May Submission7165 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Level-Navi Agent: A Framework and benchmark for Web Search Agents
ACL ARR 2025 May Submission7164 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
ALRPHFS：Adversarially Learned Risk Patterns with Hierarchical Fast & Slow Reasoning for Robust Agent Defense
ACL ARR 2025 May Submission7162 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Detecting Vision-Language Model Hallucinations before Generation
ACL ARR 2025 May Submission7161 Authors
- 20 May 2025 (modified: 04 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Evaluating Vision–Language and Large Language Models for Automated Student Assessment in Indonesian Classrooms
ACL ARR 2025 May Submission7160 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
ACL ARR 2025 May Submission7155 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Argus: Disambiguating User Queries for Tool-Calling Agents via Uncertainty Quantification
ACL ARR 2025 May Submission7153 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Valuable Hallucinations: Realizable Non-Realistic Propositions
ACL ARR 2025 May Submission7152 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Generative Annotation for ASR Named Entity Correction
ACL ARR 2025 May Submission7140 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading
ACL ARR 2025 May Submission7138 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Personalized LLM Decoding via Contrasting Personal Preference
ACL ARR 2025 May Submission7136 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Through the Valley: Path to Effective Long CoT Training for Small Language Models
ACL ARR 2025 May Submission7135 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Self-Refine Learning in LLM Mult-Agent Systems for Norm Cognition and Compliance
ACL ARR 2025 May Submission7133 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities
ACL ARR 2025 May Submission7130 Authors
- 20 May 2025 (modified: 07 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding
ACL ARR 2025 May Submission7127 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
TextSleuth: Towards Explainable Tampered Text Detection
ACL ARR 2025 May Submission7122 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks
ACL ARR 2025 May Submission7115 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Beyond Bouba & Kiki: Does Sound Symbolism scale across 27 Languages?
ACL ARR 2025 May Submission7109 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Insights into using temporal coordinated behaviour to explore connections between social media posts and influence
ACL ARR 2025 May Submission7104 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
AfriVox: Probing Multilingual and Accent robustness of Speech LLMs
ACL ARR 2025 May Submission7103 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning
ACL ARR 2025 May Submission7102 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment
ACL ARR 2025 May Submission7100 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Enhancing LLM Character-Level Manipulation via Divide and Conquer
ACL ARR 2025 May Submission7097 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
ACL ARR 2025 May Submission7096 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone