ACL ARR 2025 February Submissions

Does Table Source Matter? Benchmarking and Improving Multimodal Scientific Table Understanding and Reasoning
ACL ARR 2025 February Submission354 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation
ACL ARR 2025 February Submission351 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework
ACL ARR 2025 February Submission349 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
The Mirage of Model Editing: Revisiting Evaluation in the Wild
ACL ARR 2025 February Submission348 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Instruction Bootstrapped Preference Optimization: Improving Model Alignment with a Better Instruction
ACL ARR 2025 February Submission346 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs
ACL ARR 2025 February Submission345 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
ACL ARR 2025 February Submission344 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
CoT-Valve: Length-Compressible Chain-of-Thought Tuning
ACL ARR 2025 February Submission343 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Authorship Verification Using Cloze Test with Large Language Models
ACL ARR 2025 February Submission342 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation
ACL ARR 2025 February Submission340 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis
ACL ARR 2025 February Submission335 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning
ACL ARR 2025 February Submission332 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models
ACL ARR 2025 February Submission331 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
How to Train a Model on a Cheap Cluster with Low Cost using Block Coordinate Descent
ACL ARR 2025 February Submission324 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Training Long-Context LLMs Efficiently via Chunk-wise Optimization
ACL ARR 2025 February Submission320 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction
ACL ARR 2025 February Submission319 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning
ACL ARR 2025 February Submission318 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units
ACL ARR 2025 February Submission317 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance Model Safety Guardrail to Potential Attacks
ACL ARR 2025 February Submission316 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models
ACL ARR 2025 February Submission309 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
iTool: Boosting Tool Use of Large Language Models via Iterative Reinforced Fine-Tuning
ACL ARR 2025 February Submission302 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agentic Tasks with Large Language Models
ACL ARR 2025 February Submission299 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA
ACL ARR 2025 February Submission296 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
Multi-Mission Tool Bench: Assessing the Robustness of LLM based Agents through Related and Dynamic Missions
ACL ARR 2025 February Submission294 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
ACL ARR 2025 February Submission293 Authors
- 06 Feb 2025 (modified: 09 May 2025)
- ACL ARR 2025 February Submission
- Readers: Everyone