Contrastive Knowledge Transfer and Robust Optimization for Secure Alignment of Large Language Models
arxiv.org·1d
✨Model optimizations in LLMs
Flag this post
DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models
arxiv.org·1d
💬Prompt optimizations for LLM serving
Flag this post
LLM-Centric RAG with Multi-Granular Indexing and Confidence Constraints
arxiv.org·1d
🔍Retrieval-augmented generation
Flag this post
Testing Cross-Lingual Text Comprehension In LLMs Using Next Sentence Prediction
arxiv.org·5d
🔍Retrieval-augmented generation
Flag this post
Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions
arxiv.org·1d
🤖Agents using LLMs
Flag this post
AstuteRAG-FQA: Task-Aware Retrieval-Augmented Generation Framework for Proprietary Data Challenges in Financial Question Answering
arxiv.org·1d
🔍Retrieval-augmented generation
Flag this post
Do LLMs Signal When They're Right? Evidence from Neuron Agreement
arxiv.org·4d
🔢Quantization of LLMs
Flag this post
Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+
arxiv.org·1d
✨Model optimizations in LLMs
Flag this post
Culture Cartography: Mapping the Landscape of Cultural Knowledge
arxiv.org·1d
✨Model optimizations in LLMs
Flag this post
Reasoning Models Sometimes Output Illegible Chains of Thought
arxiv.org·1d
✨Model optimizations in LLMs
Flag this post
Questionnaire meets LLM: A Benchmark and Empirical Study of Structural Skills for Understanding Questions and Responses
arxiv.org·4d
💬Prompt optimizations for LLM serving
Flag this post
Un-Attributability: Computing Novelty From Retrieval & Semantic Similarity
arxiv.org·1d
🔍Retrieval-augmented generation
Flag this post
Identifying the Periodicity of Information in Natural Language
arxiv.org·1d
🔍Retrieval-augmented generation
Flag this post
VISTA Score: Verification In Sequential Turn-based Assessment
arxiv.org·1d
💬Prompt optimizations for LLM serving
Flag this post
StreetMath: Study of LLMs' Approximation Behaviors
arxiv.org·4d
✨Model optimizations in LLMs
Flag this post
MVeLMA: Multimodal Vegetation Loss Modeling Architecture for Predicting Post-fire Vegetation Loss
arxiv.org·1d
✨Model optimizations in LLMs
Flag this post
Reward Collapse in Aligning Large Language Models
arxiv.org·4d
💬Prompt optimizations for LLM serving
Flag this post
Thought Branches: Interpreting LLM Reasoning Requires Resampling
arxiv.org·1d
✨Model optimizations in LLMs
Flag this post
Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error
arxiv.org·4d
✨Model optimizations in LLMs
Flag this post
Rethinking Cross-lingual Alignment: Balancing Transfer and Cultural Erasure in Multilingual LLMs
arxiv.org·4d
🔍Retrieval-augmented generation
Flag this post