Member Only Content
To access all features, please consider upgrading to full Membership.
AI Ecosystem Intelligence Explorer
21 of 52 articles
Introducing Multimodal Llama 3.2
Complete this Guided Project in under 2 hours. Join our new short course, Introducing Multimodal Llama 3.2, and learn from Amit Sangani, Senior Director of…
The Effect of Sampling Temperature on Problem Solving in Large Language Models
In this research study, we empirically investigate the effect of sampling temperature on the performance of Large Language Models (LLMs) on various problem-solving tasks. We created a multiple-choice question-and-answer (MCQA) exam by randomly sampling problems from standard LLM benchmarks. Then, we used nine popular LLMs with five prompt-engineering techniques to solve the MCQA problems while increasing the sampling temperature from 0.0 to 1.6. Despite anecdotal reports to the contrary, our empirical results indicate that changes in temperature from 0.0 to 1.0 do not have a statistically significant impact on LLM performance for problem-solving tasks. In addition, these results appear to generalize across LLMs, prompt-engineering techniques, and problem domains. All code, data, and supplemental materials are available on GitHub at: https://github.com/matthewrenze/jhu-llm-temperature
IBM’s Granite foundation model: A detailed look at its training data
While many AI model developers publicly release research papers and their data training approaches, we’ll focus on one model in particular– IBM’s Granite model, where IBM has gone one step further and released their specific training data.
The Geometry of Concepts: Sparse Autoencoder Feature Structure
Sparse autoencoders have recently produced dictionaries of high-dimensional vectors corresponding to the universe of concepts represented by large language models. We find that this concept universe has interesting structure at three levels: 1) The “atomic” small-scale structure contains “crystals” whose faces are parallelograms or trapezoids, generalizing well-known examples such as (man-woman-king-queen). We find that the quality of such parallelograms and associated function vectors improves greatly when projecting out global distractor directions such as word length, which is efficiently done with linear discriminant analysis. 2) The “brain” intermediate-scale structure has significant spatial modularity; for example, math and code features form a “lobe” akin to functional lobes seen in neural fMRI images. We quantify the spatial locality of these lobes with multiple metrics and find that clusters of co-occurring features, at coarse enough scale, also cluster together spatially far more than one would expect if feature geometry were random. 3) The “galaxy” scale large-scale structure of the feature point cloud is not isotropic, but instead has a power law of eigenvalues with steepest slope in middle layers. We also quantify how the clustering entropy depends on the layer.
From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization
Although many studies have investigated and reduced hallucinations in large language models (LLMs) for single-document tasks, research on hallucination in multi-document summarization (MDS) tasks remains largely unexplored. Specifically, it is unclear how the challenges arising from handling multiple documents (e.g., repetition and diversity of information) affect models outputs. In this work, we investigate how hallucinations manifest in LLMs when summarizing topic-specific information from multiple documents. Since no benchmarks exist for investigating hallucinations in MDS, we use existing news and conversation datasets, annotated with topic-specific insights, to create two novel multi-document benchmarks. When evaluating 5 LLMs on our benchmarks, we observe that on average, up to 75% of the content in LLM-generated summary is hallucinated, with hallucinations more likely to occur towards the end of the summaries. Moreover, when summarizing non-existent topic-related information, gpt-3.5-turbo and GPT-4o still generate summaries about 79.35% and 44% of the time, raising concerns about their tendency to fabricate content. To understand the characteristics of these hallucinations, we manually evaluate 700+ insights and find that most errors stem from either failing to follow instructions or producing overly generic insights. Motivated by these observations, we investigate the efficacy of simple post-hoc baselines in mitigating hallucinations but find them only moderately effective. Our results underscore the need for more effective approaches to systematically mitigate hallucinations in MDS. We release our dataset and code at github.com/megagonlabs/Hallucination_MDS.
How to tell if an LLM is just guessing
[Paper: Detecting hallucinations in large language models using semantic entropy]
Detecting when LLMs are Uncertain
A deep dive into a new reasoning technique called Entropix.
You Should Probably Pay Attention to Tokenizers
Last week I was helping a friend of mine to get one of his new apps off the ground. I can’t speak much about it at the moment, other than like most apps nowadays it has some AI sprinkled over it. Ok, maybe a bit maybe more just a bit – depends on the way you look at it, I suppose. There is a Retrieval-augmented generation (RAG) hiding somewhere in most of the AI apps. RAG is still all the RAGe – it even has its own Wikipedia page now! I’m not sure if anyone is tracking how fast a term reaches the point where it gets its own Wiki page but RAG must be somewhere near the top of the charts.
Can Large Language Models Reason?
What should we believe about the reasoning abilities of today’s large language models? As the headlines above illustrate, there’s a debate raging over whether these enormous pre-trained neural networks have achieved humanlike reasoning abilities, or whether their skills are in fact “a mirage.”