PODCAST

LlamaCast

Shahriar Shariati

Daily podcast about the published articles in the LLM field.

technology mathematics

All Episodes

8:09

Molmo and PixMo

LlamaCast ·

2024/10/18

🔓 Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal ModelsThis research paper introduces Molmo, a new family of vision-language models (VLMs) that surpasses existing open-weight models in performance while maintaining open weights, data, and code. The key innovation is the collection of a large, detailed image caption dataset using speech-based descriptions, avoiding reliance on synthetic data generated by proprietary VLMs. Molmo is trained on this dataset, along with a

9:26

Self-Taught Evaluators

LlamaCast ·

2024/10/18

🔄 Self-Taught EvaluatorsThis research paper explores the development of self-taught language model evaluators. Instead of relying on costly human annotations, this approach utilizes synthetic data generated by the model itself. The method iteratively trains an LLM-as-a-Judge by creating contrasting response pairs, generating reasoning traces, and fine-tuning the model on this synthetic data. The research demonstrates that this method significantly improves the accuracy of the evaluator on

14:29

Larger LLMs Become Less Reliable

LlamaCast ·

2024/10/18

⚠️ Larger and more instructable language models become less reliableThis research paper from Nature explores the relationship between the size and instructability of large language models (LLMs) and their reliability. The study finds that while larger, more instructable LLMs tend to perform better on complex tasks, they become less reliable in handling simple tasks, often producing plausible but incorrect answers instead of safely avoiding them. Additionally, the study highlights the limitations of

8:09

Logic-of-Thought

LlamaCast ·

2024/10/18

💭 Logic-of-Thought: Injecting Logic into Contexts for Full Reasoning in LLMsThis research paper introduces Logic-of-Thought (LoT), a novel prompting method designed to enhance logical reasoning in large language models. LoT extracts propositions and logical relations from input text, expands them using logical rules, and reintegrates this information into the original prompt. Unlike existing techniques, LoT preserves information and guides the model's reasoning process while leveraging its natural

10:43

Moshi

LlamaCast ·

2024/10/18

🟢 Moshi: a speech-text foundation model for real-time dialogueThe paper discusses a new multimodal foundation model called Moshi designed for real-time, full-duplex spoken dialogue. This model uses a text-based LLM called Helium to provide reasoning abilities and a neural audio codec called Mimi to encode audio into tokens. Moshi is innovative because it can handle overlapping speech and model both the user's and the system's speech in a single stream. The paper also explores the model's

6:39

Jailbreaking Large Language Models with Symbolic...

LlamaCast ·

2024/10/18

🔑 Jailbreaking Large Language Models with Symbolic MathematicsThis research paper investigates a new vulnerability in AI safety mechanisms by introducing MathPrompt, a technique that utilizes symbolic mathematics to bypass LLM safety measures. The paper demonstrates that encoding harmful natural language prompts into mathematical problems allows LLMs to generate harmful content, despite being trained to prevent it. Experiments across 13 state-of-the-art LLMs show a high success rate for MathPrompt,

8:19

LLMs Still Can't Plan; Can LRMs?

LlamaCast ·

2024/10/18

📈 LLMs Still Can't Plan; Can LRMs?The paper "LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench" investigates the ability of large language models (LLMs) to plan, using a benchmark called PlanBench. The authors find that while OpenAI's new "Large Reasoning Model" (LRM) o1 shows significant improvement in planning abilities, it still falls short of fully achieving the task. This research highlights the need for further investigation into the accuracy, efficiency,

8:28

A Comprehensive Evaluation of Quantized...

LlamaCast ·

2024/10/18

📏 A Comprehensive Evaluation of Quantized Instruction-Tuned LLMsThis paper, titled "A Comprehensive Evaluation of Quantized Instruction-Tuned Large Language Models: An Experimental Analysis up to 405B," examines the performance of large language models (LLMs) after they have been compressed using various quantization methods. The authors assess the impact of these techniques on different task types and model sizes, including the very large 405B parameter Llama 3.1 model. They explore how different

8:38

On the Diagram of Thought

LlamaCast ·

2024/10/17

🧠 On the Diagram of ThoughtThis paper introduces a new framework called Diagram of Thought (DoT) that models how large language models (LLMs) reason. Unlike traditional methods that represent reasoning as linear chains or trees, DoT utilizes a directed acyclic graph (DAG) structure. This structure allows LLMs to navigate complex reasoning pathways while ensuring logical consistency. By incorporating feedback mechanisms and leveraging auto-regressive next-token prediction, DoT enables LLMs to

49 results

LlamaCast

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs