10). Measuring Bullshit in Language Games Played by ChatGPT – proposes that LLM-based chatbots play the ‘language game of bullshit’; by asking ChatGPT to generate scientific articles on topics where it has no knowledge or competence, the authors were able to provide a reference
@dair_ai
-
Survey on LLM-as-a-Judge: Building Reliable Evaluation Systems
By
–
7). Survey on LLM-as-a-Judge – provides a comprehensive survey of LLM-as-a-Judge, including a deeper discussion on how to build reliable LLM-as-a-Judge systems.
-
TÜLU 3 releases state-of-the-art open post-trained models
By
–
8). TÜLU 3 – releases a family of fully-open state-of-the-art post-trained models, alongside its data, code, and training recipes, serving as a comprehensive guide for modern post-training techniques.
-
Qwen2.5 Achieves State-of-the-Art Math Reasoning Surpassing GPT-4o
By
–
5). High-Level Automated Reasoning – extends in-context learning through high-level automated reasoning; achieves state-of-the-art accuracy (79.6%) on the MATH benchmark with Qwen2.5-7B-Instruct, surpassing GPT-4o (76.6%) and Claude 3.5 (71.1%).
-
Star Attention: Efficient LLM Inference for Long Sequences
By
–
6). Star Attention: Efficient LLM Inference over Long Sequences – introduces Star Attention, a two-phase attention mechanism that processes long sequences by combining blockwise-local attention for context encoding with sequence-global attention for query processing and token
-
o1 Replication: Distillation and Fine-tuning for Math Reasoning
By
–
3). o1 Replication Journey – Part 2 – shows that combining simple distillation from o1's API with supervised fine-tuning significantly boosts performance on complex math reasoning tasks…
-
LLM-Brained GUI Agents: Survey of Techniques and Applications
By
–
4). LLM-Brained GUI Agents – presents a survey of LLM-brained GUI Agents, including techniques and applications.
-
NVIDIA Fugatto: Generative AI Model for Sound Creation
By
–
2). Fugatto – a new generative AI sound model (presented by NVIDIA) that can create and transform any combination of music, voices, and sounds using text and audio inputs, trained on 2.5B…
-
HtmlRAG: Novel HTML-Based Approach for RAG Systems
By
–
10). HtmlRAG – a novel approach that proposes using HTML instead of plain text as the format for building RAG systems; the key finding is that preserving HTML structure provides richer semantic and structural information compared to plain text conversion, which typically loses
-
Mixture of Transformers: Sparse Multimodal Architecture for Efficiency
By
–
9). Mixture of Transformers – introduce Mixture-of-Transformers (MoT), a new sparse multi-modal transformer architecture that matches the performance of traditional models while using only about half the computational resources for text and image processing.