ACL ARR 2025 May Submissions

SciCompanion: Graph-Grounded Reasoning for Structured Evaluation of Scientific Arguments
ACL ARR 2025 May Submission5917 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
LMUNIT: Fine-grained Evaluation with Natural Language Unit Tests
ACL ARR 2025 May Submission5904 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
ACL ARR 2025 May Submission5903 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection
ACL ARR 2025 May Submission5899 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Cluster-Driven Expert Pruning for Mixture-of-Experts Large Language Models
ACL ARR 2025 May Submission5898 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Database-Augmented Query Representation for Information Retrieval
ACL ARR 2025 May Submission5897 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Attend or Perish: Benchmarking Attention in Algorithmic Reasoning
ACL ARR 2025 May Submission5895 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Data Generation for Policy-Grounded Stance Detection using Sparse Supervision
ACL ARR 2025 May Submission5892 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Enhancing Hate Speech Classifiers through a Gradient-assisted Counterfactual Text Generation Strategy
ACL ARR 2025 May Submission5887 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Beyond Single Models: Mitigating Multimodal Hallucinations via Adaptive Token Ensemble Decoding
ACL ARR 2025 May Submission5886 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Zero-Shot Open-Schema Entity Structure Discovery
ACL ARR 2025 May Submission5882 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
SS-MPC: A Sequence-Structured Multi-Party Conversation System
ACL ARR 2025 May Submission5881 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Revealing the Inherent Instructability of Pre-Trained Language Models
ACL ARR 2025 May Submission5877 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
An Information-Theoretic Study of RLHF-Induced Uniformity in Large Language Model Outputs
ACL ARR 2025 May Submission5874 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design
ACL ARR 2025 May Submission5872 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Benchmarking Debiasing Methods for LLM-based Parameter Estimates
ACL ARR 2025 May Submission5868 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Token-Aware Editing of Internal Activations for Large Language Model Alignment
ACL ARR 2025 May Submission5867 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
RAISE: Reinforced Adaptive Instruction Selection For Large Language Models
ACL ARR 2025 May Submission5865 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Consensus Sparse Attention: A Memory and Computation Efficient Mechanism Based on Inter-Head Consensus
ACL ARR 2025 May Submission5860 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty?
ACL ARR 2025 May Submission5859 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning
ACL ARR 2025 May Submission5857 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
The Guessing Dilemma: Unveiling LLMs' Reasoning Changes Under Short-Path Prompting
ACL ARR 2025 May Submission5856 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
MMATH: A Multilingual Benchmark for Mathematical Reasoning
ACL ARR 2025 May Submission5849 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
ACL ARR 2025 May Submission5845 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Where You Go is Who You Are: Behavioral Theory-Guided LLMs for Inverse Reinforcement Learning
ACL ARR 2025 May Submission5843 Authors
- 20 May 2025 (modified: 29 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone