ACL 2025
4,324 papers
Top Research Directions
Research directions most represented by ACL 2025 papers.
Top Authors
Impactful Papers
Papers from ACL 2025 that shaped research clusters.
Foundational
LongSafety: Enhance Safety for Long-Context LLMs
foundational
Safety Alignment Degradation in Long Con
Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
foundational
Aligning Retrieval with Functional Utili
What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs
foundational
Safety Alignment Degradation in Long Con
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators
foundational
Bridging the Performance Correctness Gap
Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Prefer
foundational
The Length Hallucination Tradeoff in Vis
Fine-Grained Constraint Generation-Verification for Improved Instruction-Following
foundational
Decomposing Complex Instructions into At
When Will the Tokens End? Graph-Based Forecasting for LLMs Output Length
foundational
Latent Foresight for Adaptive Language M
PAP2PAT: Benchmarking Outline-Guided Long-Text Patent Generation with Patent-Paper Pairs
foundational
The Tradeoff Between Stylistic Alignment
GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classi
foundational
Hierarchical Classification of Multiling
Influential
In-Domain African Languages Translation Using LLMs and Multi-armed Bandits
influential
Bayesian Action Selection via Thompson S
PersonaX: A Recommendation Agent-Oriented User Modeling Framework for Long Behavior Sequence
influential
Semantic Personas from Behavioral Trajec
Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions
influential
The Fluency Control Tradeoff in Language
Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles
influential
Supervised Error Detection Using Seconda
Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models
influential
Functional Specialization of Retrieval H
Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process
influential
Unpaired Preference Optimization with Bi
dutir914 at SemEval-2025 Task 1: An integrated approach for Multimodal Idiomaticity Representations
influential
Interleaved Multimodal Chain of Thought
UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis
influential
Resolving Semantic Ambiguity in Graphica
LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and
influential
Learning to Recover from Compounding Err
Papers
« prev Page 87/87