Related papers: Integrating a large-scale testing campaign in the …
We present LLM-KT, a flexible framework designed to enhance collaborative filtering (CF) models by seamlessly integrating LLM (Large Language Model)-generated features. Unlike existing methods that rely on passing LLM-generated features as…
Large-scale LLM training requires collective communication libraries to exchange data among distributed GPUs. As a company dedicated to building and operating large-scale GPU training clusters, we encounter several challenges when using…
As the field of Large Language Models (LLMs) evolves at an accelerated pace, the critical need to assess and monitor their performance emerges. We introduce a benchmarking framework focused on knowledge graph engineering (KGE) accompanied…
We introduce Cognitive Kernel, an open-source agent system towards the goal of generalist autopilots. Unlike copilot systems, which primarily rely on users to provide essential state information (e.g., task descriptions) and assist users by…
The complexity of knowledge production on complex systems is well-known, but there still lacks knowledge framework that would both account for a certain structure of knowledge production at an epistemological level and be directly…
We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent variable. By optimizing the…
Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble…
Precise, correct feedback is crucial for effectively training large language models (LLMs) in code reinforcement learning. However, synthesizing high-quality test cases remains a profoundly challenging and unsolved problem. In this work, we…
In spite of machine learning's rapid growth, its engineering support is scattered in many forms, and tends to favor certain engineering stages, stakeholders, and evaluation preferences. We envision a capability-based framework, which uses…
Current learning algorithms face many difficulties in learning simple patterns and using them to learn more complex ones. They also require more examples than humans do to learn the same pattern, assuming no prior knowledge. In this paper,…
Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…
Knowledge Graphs (KG) provide us with a structured, flexible, transparent, cross-system, and collaborative way of organizing our knowledge and data across various domains in society and industrial as well as scientific disciplines. KGs…
Large language models (LLMs) have proven to be highly effective for solving complex reasoning tasks. Surprisingly, their capabilities can often be improved by iterating on previously generated solutions. In this context, a reasoning plan…
A central challenge for ensuring the success of software projects is to assure the convergence of developers' and users' views. While the availability of large amounts of user data from social media, app store reviews, and support channels…
Scientific applications that involve simulation ensembles can be accelerated greatly by using experiment design methods to select the best simulations to perform. Methods that use machine learning (ML) to create proxy models of simulations…
\textit{Background:} The use of large language models in software testing is growing fast as they support numerous tasks, from test case generation to automation, and documentation. However, their adoption often relies on informal…
The rapid iteration and frequent updates of modern video games pose significant challenges to the efficiency and specificity of testing. Although automated playtesting methods based on Large Language Models (LLMs) have shown promise, they…
The rapid development of artificial intelligence has led to marked progress in the field. One interesting direction for research is whether Large Language Models (LLMs) can be integrated with structured knowledge-based systems. This…
Behavior cloning has shown success in many sequential decision-making tasks by learning from expert demonstrations, yet they can be very sample inefficient and fail to generalize to unseen scenarios. One approach to these problems is to…
Distributed knowledge based applications in open domain rely on common sense information which is bound to be uncertain and incomplete. To draw the useful conclusions from ambiguous data, one must address uncertainties and conflicts…