ACL ARR 2025 February Submissions

CAI: Caption-Sensitive Attention Intervention for Mitigating Object Hallucination in Large Vision-Language Models
ACL ARR 2025 February Submission3684 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Dynamic Evil Score-Guided Decoding: An Efficient Decoding Framework For Red-Team Model
ACL ARR 2025 February Submission3683 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Prompt-Guided Internal States for Hallucination Detection of Large Language Models
ACL ARR 2025 February Submission3676 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Consolidating and Developing Benchmarking Datasets for the Nepali Natural Language Understanding Tasks
ACL ARR 2025 February Submission3670 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Correcting Annotator Bias in Training Data: Population-Aligned Instance Replication (PAIR)
ACL ARR 2025 February Submission3668 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Efficiently Bridging Protein Language Model and Large Language Model with a Cross-modal Lightweight Adapter
ACL ARR 2025 February Submission3665 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Spoken document retrieval for an unwritten language
ACL ARR 2025 February Submission3663 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMs
ACL ARR 2025 February Submission3658 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
RASPberry: Retrieval-Augmented Monte Carlo Tree Self-Play with Reasoning Consistency for Multi-Hop Question Answering
ACL ARR 2025 February Submission3656 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Relation Extraction or Pattern Matching? Unravelling the Generalisation Limits of Language Models for Biographical RE
ACL ARR 2025 February Submission3655 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
ACL ARR 2025 February Submission3651 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking
ACL ARR 2025 February Submission3650 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors
ACL ARR 2025 February Submission3648 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Hierarchical Attention Generates Better Proofs
ACL ARR 2025 February Submission3646 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Training and Inference Efficiency of Encoder-Decoder Speech Models
ACL ARR 2025 February Submission3643 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
On Large Language Models for Effective Red Teaming
ACL ARR 2025 February Submission3639 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
ACL ARR 2025 February Submission3635 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
User-Level Safety Alignment
ACL ARR 2025 February Submission3630 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
ACL ARR 2025 February Submission3628 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
UniCodec: Unified Audio Codec with Single Domain-Adaptive Codebook
ACL ARR 2025 February Submission3621 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Two Are Better than One: Context Window Extension with Multi-Grained Self-Injection
ACL ARR 2025 February Submission3620 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Rethinking the Evaluation of Alignment Methods: Insights into Diversity, Generalisation, and Safety
ACL ARR 2025 February Submission3618 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Guardrails in Logit Space: Safety Token Regularization for LLM Alignment Preservation
ACL ARR 2025 February Submission3617 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Unveiling Modality Bias: Automated Sample-Specific Analysis for Multimodal Misinformation Benchmarks
ACL ARR 2025 February Submission3612 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Harnessing LLM to Attack LLM-Guarded Text-to-Image Models
ACL ARR 2025 February Submission3608 Authors
- 15 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone