ACL ARR 2025 May Submissions

LILaC: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop Retrieval
ACL ARR 2025 May Submission7723 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
PersianMedQA: Language-Centric Evaluation of LLMs in the Persian Medical Domain
ACL ARR 2025 May Submission7719 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
LC-Eval: A Bilingual Multi-Task Evaluation Benchmark for Long-Context Understanding
ACL ARR 2025 May Submission7717 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study
ACL ARR 2025 May Submission7708 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing
ACL ARR 2025 May Submission7707 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
HealthCards: Exploring Text-to-Image Generation as Visual Aids for Healthcare Knowledge Democratizing and Education
ACL ARR 2025 May Submission7706 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Causal AI Assistant: Facilitating Causal Data Science with Large Language Models
ACL ARR 2025 May Submission7702 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Letriever: Leveraging LLMs as Context Retrievers with Reasoning Capabilities
ACL ARR 2025 May Submission7695 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Learning to Align: Addressing Character Frequency Distribution Shifts in Handwritten Text Recognition
ACL ARR 2025 May Submission7693 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
One Task Vector is not Enough: A Large-Scale Study for In-Context Learning
ACL ARR 2025 May Submission7689 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
TopoMSG: A Topology-Aware Multi-Scale Graph Network for Social Bot Detection
ACL ARR 2025 May Submission7688 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Schema as Parameterized Tools for Universal Information Extraction
ACL ARR 2025 May Submission7686 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Orthogonal Finetuning Made Scalable
ACL ARR 2025 May Submission7684 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression
ACL ARR 2025 May Submission7681 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups
ACL ARR 2025 May Submission7678 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark
ACL ARR 2025 May Submission7677 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
WISP: A Stealthy Word-level Backdoor Attack via Semantic Influence and LLM-Guided Injection
ACL ARR 2025 May Submission7676 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation
ACL ARR 2025 May Submission7675 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Seeing Culture: A Benchmark for Visual Reasoning and Grounding
ACL ARR 2025 May Submission7665 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
AuditLLM: A Compact and Domain-Specialized Large Language Model Family for Intelligent Auditing via Two-Stage Continual Pre-Training
ACL ARR 2025 May Submission7664 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
MARCO-Law: Marginal-Aware Reinforcement Learning for Legal Tool Orchestration
ACL ARR 2025 May Submission7663 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Can Language Models Follow Multiple Turns of Entangled Instructions?
ACL ARR 2025 May Submission7660 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
ACL ARR 2025 May Submission7657 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
Graph-O-Planner: Injecting Graph Neural Tool Embeddings into LLMs for Efficient and Accurate Task Execution
ACL ARR 2025 May Submission7652 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone
MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling
ACL ARR 2025 May Submission7647 Authors
- 20 May 2025 (modified: 03 Jul 2025)
- ACL ARR 2025 May Submission
- Readers: Everyone