ACL ARR 2025 May Submissions

SemiHVision: Enhancing Medical Multimodal Models with a Semi-Human Annotated Dataset and Fine-Tuned Instruction Generation
ACL ARR 2025 May Submission6070 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets
ACL ARR 2025 May Submission6069 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Conflicts in Texts: Data, Implications and Challenges
ACL ARR 2025 May Submission6068 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models
ACL ARR 2025 May Submission6066 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
LlmFixer: Fix the Helpfulness of Defensive Large Language Models
ACL ARR 2025 May Submission6064 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Internal Chain-of-Thought: Empirical Evidence for Layer‑wise Subtask Scheduling in LLMs
ACL ARR 2025 May Submission6050 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Investigating the Link Between Factual Prevalence and Hallucinations in LLMs via Academic Author Prediction Tasks
ACL ARR 2025 May Submission6049 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Diagnosing Visual Reasoning: Challenges, Insights, and a Path Forward
ACL ARR 2025 May Submission6048 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
ReasonVOS: Benchmarking and Addressing Spatiotemporal-Semantic Reasoning in Instruction-Guided Video Segmentation
ACL ARR 2025 May Submission6044 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Multi-Turn Multi-Modal Question Clarification for Enhanced Conversational Understanding
ACL ARR 2025 May Submission6031 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
CARE: Causal-Aware Robust Estimation for Hallucination Mitigation in Large Vision Language Models
ACL ARR 2025 May Submission6030 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
RoRA-VLM: Robust Retrieval Augmentation for Vision Language Models
ACL ARR 2025 May Submission6026 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
ICL-Bandit: Relevance Labeling in Advertisement Recommendation Systems via LLM
ACL ARR 2025 May Submission6015 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Breaking the Attention Trap in Code LLMs: A Rejection Sampling Approach to Enhance Code Execution Prediction
ACL ARR 2025 May Submission6014 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
EnDive: A Cross-Dialect Benchmark for Fairness and Performance in Large Language Models
ACL ARR 2025 May Submission6008 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Spatial Layouts in News Homepages Capture Human Preferences
ACL ARR 2025 May Submission6005 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
A Comprehensive Survey on the Trustworthiness of Large Language Models in Healthcare
ACL ARR 2025 May Submission6002 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Enhancing Chain-of-Thought Reasoning via Neuron Activation Differential Analysis
ACL ARR 2025 May Submission6001 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
MDR: Memory Distillation and Reproduction for Personalized Dialogue Generation
ACL ARR 2025 May Submission5999 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety
ACL ARR 2025 May Submission5994 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context
ACL ARR 2025 May Submission5990 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models
ACL ARR 2025 May Submission5981 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
I Am No One: Style-Aware Paraphrasing for Text Anonymization
ACL ARR 2025 May Submission5977 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns
ACL ARR 2025 May Submission5962 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
COUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down Projection
ACL ARR 2025 May Submission5959 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone