Large Language Models

START: Self-taught Reasoner with Tools EMNLP 2025 StarVector: Generating Scalable Vector Graphics Code from Images and Text CVPR 2025 StateAct: Enhancing LLM Base Agents via Self-prompting and State-tracking ACL 2025 StateCloud at Critical Questions Generation: Prompt Engineering for Critical Question Generation ACL 2025 State Space Models are Strong Text Rerankers NAACL 2025 State space models, emergence, and ergodicity: How many parameters are needed for stable predictions? L4DC 2025 Statistical Hypothesis Testing for Auditing Robustness in Language Models ICML 2025 STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs ICLR 2025 StealthInk: A Multi-bit and Stealthy Watermark for Large Language Models ICML 2025 Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring NAACL 2025 STEAM: A Semantic-Level Knowledge Editing Framework for Large Language Models EMNLP 2025 STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models EMNLP 2025 Steering Conversational Large Language Models for Long Emotional Support Conversations ACL 2025 Steering LLM Reasoning Through Bias-Only Adaptation EMNLP 2025 Steering off Course: Reliability Challenges in Steering Language Models ACL 2025 Steer LLM Latents for Hallucination Detection ICML 2025 STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing ACL 2025 Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo ICLR 2025 StepER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Models EMNLP 2025 Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning EMNLP 2025 Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models EMNLP 2025 Stepwise Informativeness Search for Improving LLM Reasoning EMNLP 2025 Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoning EMNLP 2025 S*: Test Time Scaling for Code Generation EMNLP 2025 Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework EMNLP 2025