Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies
Large language models (LLMs) have demonstrated remarkable performance across a wide
array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent …
array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent …
A survey of large language models
Language is essentially a complex, intricate system of human expressions governed by
grammatical rules. It poses a significant challenge to develop capable AI algorithms for …
grammatical rules. It poses a significant challenge to develop capable AI algorithms for …
Metamath: Bootstrap your own mathematical questions for large language models
Large language models (LLMs) have pushed the limits of natural language understanding
and exhibited excellent problem-solving ability. Despite the great success, most existing …
and exhibited excellent problem-solving ability. Despite the great success, most existing …
Lora learns less and forgets less
Low-Rank Adaptation (LoRA) is a widely-used parameter-efficient finetuning method for
large language models. LoRA saves memory by training only low rank perturbations to …
large language models. LoRA saves memory by training only low rank perturbations to …
LLMs can't plan, but can help planning in LLM-modulo frameworks
There is considerable confusion about the role of Large Language Models (LLMs) in
planning and reasoning tasks. On one side are over-optimistic claims that LLMs can indeed …
planning and reasoning tasks. On one side are over-optimistic claims that LLMs can indeed …
The caring machine: Feeling AI for customer care
Customer care is important for its role in relationship building. This role has traditionally
been performed by human customer agents; however, the emergence of interactive …
been performed by human customer agents; however, the emergence of interactive …
Llm self defense: By self examination, llms know they are being tricked
Large language models (LLMs) are popular for high-quality text generation but can produce
harmful content, even when aligned with human values through reinforcement learning …
harmful content, even when aligned with human values through reinforcement learning …
Trueteacher: Learning factual consistency evaluation with large language models
Factual consistency evaluation is often conducted using Natural Language Inference (NLI)
models, yet these models exhibit limited success in evaluating summaries. Previous work …
models, yet these models exhibit limited success in evaluating summaries. Previous work …
Personal llm agents: Insights and survey about the capability, efficiency and security
Since the advent of personal computing devices, intelligent personal assistants (IPAs) have
been one of the key technologies that researchers and engineers have focused on, aiming …
been one of the key technologies that researchers and engineers have focused on, aiming …
Distilling system 2 into system 1
Large language models (LLMs) can spend extra compute during inference to generate
intermediate thoughts, which helps to produce better final responses. Since Chain-of …
intermediate thoughts, which helps to produce better final responses. Since Chain-of …