Factuality challenges in the era of large language models and opportunities for fact-checking
I Augenstein, T Baldwin, M Cha… - Nature Machine …, 2024 - nature.com
The emergence of tools based on large language models (LLMs), such as OpenAI's
ChatGPT and Google's Gemini, has garnered immense public attention owing to their …
ChatGPT and Google's Gemini, has garnered immense public attention owing to their …
The mechanistic basis of data dependence and abrupt learning in an in-context classification task
G Reddy - The Twelfth International Conference on Learning …, 2023 - openreview.net
Transformer models exhibit in-context learning: the ability to accurately predict the response
to a novel query based on illustrative examples in the input sequence, which contrasts with …
to a novel query based on illustrative examples in the input sequence, which contrasts with …
Can language models handle recursively nested grammatical structures? A case study on comparing models and humans
A Lampinen - Computational Linguistics, 2024 - direct.mit.edu
How should we compare the capabilities of language models (LMs) and humans? In this
paper, I draw inspiration from comparative psychology to highlight challenges in these …
paper, I draw inspiration from comparative psychology to highlight challenges in these …
In-context principle learning from mistakes
In-context learning (ICL, also known as few-shot prompting) has been the standard method
of adapting LLMs to downstream tasks, by learning from a few input-output examples …
of adapting LLMs to downstream tasks, by learning from a few input-output examples …
Retrieval-augmented generation to improve math question-answering: Trade-offs between groundedness and human preference
For middle-school math students, interactive question-answering (QA) with tutors is an
effective way to learn. The flexibility and emergent capabilities of generative large language …
effective way to learn. The flexibility and emergent capabilities of generative large language …
What Makes Multimodal In-Context Learning Work?
Abstract Large Language Models have demonstrated remarkable performance across
various tasks exhibiting the capacity to swiftly acquire new skills such as through In-Context …
various tasks exhibiting the capacity to swiftly acquire new skills such as through In-Context …
The ARRT of Language-Models-as-a-Service: Overview of a New Paradigm and its Challenges
Some of the most powerful language models currently are proprietary systems, accessible
only via (typically restrictive) web or software programming interfaces. This is the Language …
only via (typically restrictive) web or software programming interfaces. This is the Language …
Competition-level problems are effective llm evaluators
Large language models (LLMs) have demonstrated impressive reasoning capabilities, yet
there is ongoing debate about these abilities and the potential data contamination problem …
there is ongoing debate about these abilities and the potential data contamination problem …
Do llm agents have regret? a case study in online learning and games
Large language models (LLMs) have been increasingly employed for (interactive) decision-
making, via the development of LLM-based autonomous agents. Despite their emerging …
making, via the development of LLM-based autonomous agents. Despite their emerging …
How capable can a transformer become? a study on synthetic, interpretable tasks
Transformers trained on huge text corpora exhibit a remarkable set of capabilities, eg,
performing simple logical operations. Given the inherent compositional nature of language …
performing simple logical operations. Given the inherent compositional nature of language …