ACL ARR 2025 February Submissions

A Close Look at Decomposition-based XAI-Methods for Transformer Language Models
ACL ARR 2025 February Submission7119 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
KazMMLU: Evaluating Language Models on Kazakh, Russian, and Regional Knowledge of Kazakhstan
ACL ARR 2025 February Submission7117 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Iterative Multilingual Spectral Attribute Erasure
ACL ARR 2025 February Submission7109 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System
ACL ARR 2025 February Submission7098 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
ACL ARR 2025 February Submission7097 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Using LLMs for Automated Privacy Policy Analysis: Prompt Engineering, Fine-Tuning and Explainability
ACL ARR 2025 February Submission7095 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Improving Multilingual Capabilities with Cultural and Local Knowledge \\in Large Language Models While Enhancing Native Performance
ACL ARR 2025 February Submission7086 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
ACL ARR 2025 February Submission7085 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training
ACL ARR 2025 February Submission7076 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception
ACL ARR 2025 February Submission7066 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models
ACL ARR 2025 February Submission7062 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
CER: Confidence Enhanced Reasoning in LLMs
ACL ARR 2025 February Submission7061 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
SafeVacuo: Jailbreaking Open-Source LLMs via Activation Perturbations
ACL ARR 2025 February Submission7054 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual Segments
ACL ARR 2025 February Submission7053 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
CtxWF: Context Window Focus with Global Management for LLM Agents in Multi-Document Workspace
ACL ARR 2025 February Submission7042 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Can a Single Model Master Both Multi-turn Conversations and Tool Use? CALM: A Unified Conversational Agentic Language Model
ACL ARR 2025 February Submission7041 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
S-RAG: A Novel Audit Framework for Detecting Unauthorized Use of Personal Data in RAG Systems
ACL ARR 2025 February Submission7039 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
FedDQC: Data Quality Control in Federated Instruction-tuning of Large Language Models
ACL ARR 2025 February Submission7038 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs
ACL ARR 2025 February Submission7037 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation
ACL ARR 2025 February Submission7031 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
VideoRAG: Retrieval-Augmented Generation over Video Corpus
ACL ARR 2025 February Submission7025 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding
ACL ARR 2025 February Submission7024 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
KyrgyzNER: The First NER Dataset for the Kyrgyz Language
ACL ARR 2025 February Submission7011 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Analogy Prompting: Testing Spatial Intuitions of Humans and Multimodal Models in Analogies
ACL ARR 2025 February Submission7009 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models
ACL ARR 2025 February Submission7000 Authors
- 16 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone