The Problem with Safety Classification is not just the Models
arxiv.org·4d
✨Model optimizations in LLMs
Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
arxiv.org·4d
🔍Retrieval-augmented generation
Can You Trust an LLM with Your Life-Changing Decision? An Investigation into AI High-Stakes Responses
arxiv.org·4d
✨Model optimizations in LLMs
From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs
arxiv.org·3d
🔍Retrieval-augmented generation
Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs
arxiv.org·3d
✨Model optimizations in LLMs
RATE: An LLM-Powered Retrieval Augmented Generation Technology-Extraction Pipeline
arxiv.org·4d
🔍Retrieval-augmented generation
ChatGPT Reads Your Tone and Responds Accordingly -- Until It Does Not -- Emotional Framing Induces Bias in LLM Outputs
arxiv.org·4d
💬Prompt optimizations for LLM serving
Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study
arxiv.org·5d
🔍Retrieval-augmented generation
Bridging the Gap: Enhancing News Interpretation Across Diverse Audiences with Large Language Models
arxiv.org·4d
🤖Agents using LLMs
Improving Task Diversity in Label Efficient Supervised Finetuning of LLMs
arxiv.org·4d
💬Prompt optimizations for LLM serving
Past Meets Present: Creating Historical Analogy with Large Language Models
arxiv.org·3d
🔍Retrieval-augmented generation
Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation
arxiv.org·3d
🔢Quantization of LLMs
FairReason: Balancing Reasoning and Social Bias in MLLMs
arxiv.org·2d
✨Model optimizations in LLMs
Can large language models assist choice modelling? Insights into prompting strategies and current models capabilities
arxiv.org·4d
✨Model optimizations in LLMs
RecUserSim: A Realistic and Diverse User Simulator for Evaluating Conversational Recommender Systems
arxiv.org·2d
🤖Agents using LLMs
LLM-Adapted Interpretation Framework for Machine Learning Models
arxiv.org·4d
✨Model optimizations in LLMs
RL from Teacher-Model Refinement: Gradual Imitation Learning for Machine Translation
arxiv.org·3d
🔍Retrieval-augmented generation
Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning
arxiv.org·5d
✨Model optimizations in LLMs
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
arxiv.org·4d
✨Model optimizations in LLMs
Investigating the Invertibility of Multimodal Latent Spaces: Limitations of Optimization-Based Methods
arxiv.org·2d
🔍Retrieval-augmented generation