ACL ARR 2025 May Submissions

Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance
ACL ARR 2025 May Submission3923 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLM
ACL ARR 2025 May Submission3922 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models
ACL ARR 2025 May Submission3918 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
LLM-based Contrastive Self-Supervised AMR Learning with Masked Graph Autoencoders for Fake News Detection
ACL ARR 2025 May Submission3914 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
ACL ARR 2025 May Submission3913 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
ACL ARR 2025 May Submission3910 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Mind the Blind Spots: A Focus-Level Evaluation Framework for LLM Reviews
ACL ARR 2025 May Submission3908 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering
ACL ARR 2025 May Submission3907 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Learning by Analogy: Enhancing Few-Shot Prompting for Math Word Problem Solving with Computational Graph-Based Retrieval
ACL ARR 2025 May Submission3904 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Evaluating GPT Surprisal, Linguistic Distances, and Model Size for Predicting Cross-Language Intelligibility of Non-Compositional Expressions
ACL ARR 2025 May Submission3901 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties
ACL ARR 2025 May Submission3898 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Explaining Sources of Uncertainty in Automated Fact-Checking
ACL ARR 2025 May Submission3895 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Agentic-R1: Distilled Dual-Strategy Reasoning
ACL ARR 2025 May Submission3892 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs
ACL ARR 2025 May Submission3890 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Modeling the Memory-Surpisal Trade-Off over Time: Communicative Efficiency Decreases with Lexico-Grammatical Change in Scientific English
ACL ARR 2025 May Submission3889 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
SAGE: LLM-Based Evaluation Through Selective Aggregation for Free-Form Question-Answering
ACL ARR 2025 May Submission3880 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Benchmarking the Myopic Trap: Positional Bias in Information Retrieval
ACL ARR 2025 May Submission3870 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
DeFT-X: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer
ACL ARR 2025 May Submission3869 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance
ACL ARR 2025 May Submission3867 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
ACL ARR 2025 May Submission3866 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Fine-tuning LLMs with Cross-Attention-based Weight Decay for Bias Mitigation
ACL ARR 2025 May Submission3860 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Empowering GraphRAG with Knowledge Filtering and Integration
ACL ARR 2025 May Submission3859 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
A Graph Perspective to Probe Structural Patterns of Knowledge in Large Language Models
ACL ARR 2025 May Submission3853 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
VRoPE: Rotary Position Embedding for Video Large Language Models
ACL ARR 2025 May Submission3849 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation
ACL ARR 2025 May Submission3842 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone