ACL ARR 2025 May Submissions

LLM Agents for Education: Advances and Applications
ACL ARR 2025 May Submission2294 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translation
ACL ARR 2025 May Submission2291 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention
ACL ARR 2025 May Submission2289 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Achieving Behavioral and Semantic Stealth with Low Perplexity Semantic Trigger in Aligned Language Models
ACL ARR 2025 May Submission2287 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
PLD-4: A Multi-Task Framework for Detecting and Attributing LLM-Generated Paraphrases
ACL ARR 2025 May Submission2285 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
AURORA: An Agentic Writing System Leveraging Rubric-Guided Reinforcement Learning
ACL ARR 2025 May Submission2278 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Progressive Visual Refinement for Multi-modal Summarization
ACL ARR 2025 May Submission2277 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Hallucination Localization in Video Captioning
ACL ARR 2025 May Submission2273 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
FuzzAug: Data Augmentation by Coverage-guided Fuzzing for Neural Test Generation
ACL ARR 2025 May Submission2268 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Zero-Shot Cross-Domain Dialogue State Tracking with Small LLMs: Learning to Think through Reinforcement Learning
ACL ARR 2025 May Submission2266 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction
ACL ARR 2025 May Submission2264 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges
ACL ARR 2025 May Submission2262 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Comprehensive Evaluation of Grammatical Error Correction Systems: Including and Beyond Reference-Based Metrics
ACL ARR 2025 May Submission2261 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Layer-Aware Embedding Fusion for Text Classification with LLMs
ACL ARR 2025 May Submission2256 Authors
- 19 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Reliable Response Generation in the Wild
ACL ARR 2025 May Submission2246 Authors
- 18 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
CORE-EVO: Evolutionary Search for Enhancing Commonsense Reasoning in Large Language Models
ACL ARR 2025 May Submission2242 Authors
- 18 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Atomic Calibration of LLMs in Long-Form Generations
ACL ARR 2025 May Submission2241 Authors
- 18 May 2025 (modified: 04 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Tokenizer-Aware Cross-Lingual Adaptation of Decoder-Only LLMs through Embedding Relearning and Swapping
ACL ARR 2025 May Submission2239 Authors
- 18 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders
ACL ARR 2025 May Submission2238 Authors
- 18 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
ACL ARR 2025 May Submission2236 Authors
- 18 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Superficial Self-Improved Reasoners Benefit from Model Merging
ACL ARR 2025 May Submission2233 Authors
- 18 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
TracSum: A New Benchmark for Aspect-Based Summarization with Sentence-Level Traceability in Medical Domain
ACL ARR 2025 May Submission2228 Authors
- 18 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models
ACL ARR 2025 May Submission2224 Authors
- 18 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Translating Legal Text to Code with LLMs: A Benchmark and Evaluation Framework
ACL ARR 2025 May Submission2223 Authors
- 18 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Your Mileage May Vary: How Empathy and Demographics Shape Human Preferences in LLM Responses
ACL ARR 2025 May Submission2218 Authors
- 18 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone