Generation

Improved Unbiased Watermark for Large Language Models ACL 2025 Improving Accessibility of SCOTUS Opinions: A Benchmark Study and a New Dataset for Generic Heading Prediction and Specific Heading Generation COLING 2025 Improving AI assistants embedded in short e-learning courses with limited textual content ACL 2025 Improving Aspect-Based Summarization via Contrastive Learning with Anchored Negative Examples EMNLP 2025 Improving Automatic Speech Recognition for Children's Reading Assessment with Disfluency-aware Language Models Interspeech 2025 Improving Causal Interventions in Amnesic Probing with Mean Projection or LEACE ACL 2025 Improving Consistency Identification in Task-oriented Dialogue Through Multi-Agent Collaboration IJCAI 2025 Improving Consistency in LLM Inference using Probabilistic Tokenization NAACL 2025 Improving Context Fidelity via Native Retrieval-Augmented Reasoning EMNLP 2025 Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Study COLING 2025 Improving Dialogue Discourse Parsing through Discourse-aware Utterance Clarification ACL 2025 Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples ACL 2025 Improving Fairness of Large Language Models in Multi-document Summarization ACL 2025 Improving Instruction-Following in Language Models through Activation Steering ICLR 2025 Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates EMNLP 2025 Improving LLM-as-a-Judge Inference with the Judgment Distribution EMNLP 2025 Improving LLM’s Attachment to External Knowledge In Dialogue Generation Tasks Through Entity Anonymization IJCNLP 2025 Improving Model Factuality with Fine-grained Critique-based Evaluator ACL 2025 Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations EMNLP 2025 Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL EMNLP 2025 Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution’s Characteristics ACL 2025 Improving Uncertainty Estimation through Semantically Diverse Language Generation ICLR 2025 Improving User Impression of Spoken Dialogue Systems by Controlling Para-linguistic Expression Based on Intimacy Interspeech 2025 In Benchmarks We Trust ... Or Not? EMNLP 2025 Incident Diagnosing and Reporting System Based on Retrieval Augmented Large Language Model AAAI 2025