4/ EfficientRAG – trains an auto-encoder LM to label and tag chunks; it retrieves relevant chunks, tags them as either or , and annotates chunks for continuous processing; then a filter model is trained to formulate the next-hop query based on the
@dair_ai
-
Grok-2: New Frontier Model Surpasses Claude and GPT-4
By
–
2/ Grok-2 – a new frontier model with strong code, math, and reasoning capabilities which includes a large and small model; outperforms both Claude 3.5 Sonnet and GPT-4-Turbo on the LMSYS Chatbot Arena; claims to improve capabilities including instruction following, retrieval,
-
The Art of Refusal: LLM Refusal Methods and Evaluation Benchmarks
By
–
10/ The Art of Refusal – a survey of the current methods used to achieve refusal in LLMs; provides evaluation benchmarks and metrics used to measure abstention in LLMs.
-
ThinK: Query-Dependent KV Cache Pruning for Efficiency
By
–
9/ ThinK – proposes an approach to address inefficiencies in KV cache memory consumption; it focuses on the long-context scenarios and the inference side of things; it presents a query-dependent KV cache pruning method to minimize attention weight loss while selectively pruning
-
Machine Unlearning Survey: Comprehensive Overview Generative AI
By
–
8/ Machine Unlearning Survey – provides a comprehensive survey on machine unlearning in generative AI.
-
ShieldGemma: LLM Safety Content Moderation Suite Built on Gemma
By
–
6/ ShieldGemma – offers a comprehensive suite of LLM-based safety content moderation models built on Gemma 2; includes classifiers for key harm types such as dangerous content, toxicity, hate speech, and more.
-
Claude 3.5 Sonnet Persona Agent Benchmark Evaluation
By
–
7/ Evaluating Persona Agents – proposes a benchmark to evaluate persona agent capabilities in LLMs; finds that Claude 3.5 Sonnet only has a 2.97% relative improvement in PersonaScore compared to GPT 3.5 despite being a much more advanced model.
-
Constrained Chain-of-Thought Improves LLaMA2 Reasoning Accuracy
By
–
4/ Constrained-CoT – limits the model reasoning output length without sacrificing performance; shows that constraining the reasoning of LLaMA2-70b to 100 words improves the accuracy from 36.01% (CoT) to 41.07% (CCoT) on GSM8K, while reducing the average output length by 28 words.
-
Adaptive RAG for Conversation Systems: Gating and Confidence
By
–
5/ Adaptive RAG for Conversations Sytems – develops a gating model that predicts if a conversational system requires RAG to improve its responses; shows that RAG-based conversational systems have the potential to generate high-quality responses and high generation confidence.
-
Improved RAG Self-Reasoning Framework for LLM Reliability
By
–
3/ Improved RAG with Self-Reasoning – presents an end-to-end self-reasoning framework to improve the reliability and traceability of RAG systems; leverages the reasoning trajectories generated by the LLM itself…