LLM Hallucination Correction Via Training-Time Correction, Generation-Time Correction & Augmentation Tools.
These methods are not mutually exclusive, and can be implemented in parallel for highly scaleable enterprise implementations.
The advent of LLMs, Foundation Models and Generative AI have given rise to a gold rush of sorts, with companies in a mad dash to develop the ultimate product to leverage the power of these models.
This gave rise to ambitious marketing (to say the least) and a susceptibility to identify one product or a single approach which will solve for all LLM implementation challenges.
The reality is that there is no elixir of sorts to remedy all implementation challenges; the solution most probably lies with a combination of technologies and principles.
This article covers three identified and accepted building blocks for LLM-based implementations; which can be used in concert or alone.
Training Time Correction
This approach is focused on a model level, where the model is fine-tuned with custom data.
Generation Time
Generation Time can also be referred to as inference time.
In generation time correction, a common theme is to make reasoning decisions on top of the base LLM in order to make them more reliable.
Another promising approach to rectify these flaws is self-correction, where the LLM itself is prompted or guided to fix problems in its own output.
Techniques leveraging automated feedback — either produced by the LLM itself or some external system, are of particular interest as they are a promising way to make LLM-based solutions more practical and deployable with minimal human feedback.
COVE also uses a related self-consistency approach, but without the multi-agent (multi-LLM) debate concept. Read more here.
Augmentation Tools
A third approach is to use external tools to help mitigate hallucinations, rather than relying solely on the abilities of the language model itself.
For example, retrieval-augmented generation can decrease hallucinations by using factual documents for grounding or chain-of-thought verification.
Other approaches include using tools for fact-checking or linking to external documents with attribution.
A majority of the methods for reducing hallucination can be divided into roughly three categories: training-time correction, generation-time correction and via augmentation (tool-use). ~ Source
⭐️ Follow me on LinkedIn for updates on Large Language Models ⭐️
I explore & write about all things at the intersection of AI & language; ranging from LLMs, Chatbots, Voicebots, Development Frameworks, Data-Centric latent spaces & more.
