Large Language Models

LingGym: How Far Are LLMs from Thinking Like Field Linguists? EMNLP 2025 LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoder EMNLP 2025 Linguistic Blind Spots of Large Language Models NAACL 2025 Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning ACL 2025 LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL EMNLP 2025 Linking language model predictions to human behaviour on scalar implicatures COLING 2025 LIRA: Reasoning Reconstruction via Multimodal Large Language Models ICCV 2025 LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs Interspeech 2025 Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate Questions ACL 2025 LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation EMNLP 2025 LITERA: An LLM Based Approach to Latin-to-English Translation NAACL 2025 LiteraryQA: Towards Effective Evaluation of Long-document Narrative QA EMNLP 2025 Literature discovery with natural language queries ACL 2025 Literature-Grounded Novelty Assessment of Scientific Ideas ACL 2025 LiteSearch: Efficient Tree Search with Dynamic Exploration Budget for Math Reasoning AAAI 2025 LiTransProQA: An LLM-based Literary Translation Evaluation Metric with Professional Question Answering EMNLP 2025 LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale CVPR 2025 LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis ACL 2025 LlamaPIE: Proactive In-Ear Conversation Assistants ACL 2025 Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs ACL 2025 LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing ACL 2025 LLaVA-KD: A Framework of Distilling Multimodal Large Language Models ICCV 2025 LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models ICCV 2025 LLM4VKG: Leveraging Large Language Models for Virtual Knowledge Graph Construction IJCAI 2025 LLM Agents Can Be Choice-Supportive Biased Evaluators: An Empirical Study AAAI 2025