Related papers: In-context Interference in Chat-based Large Langua…
With the recent emergence of powerful instruction-tuned large language models (LLMs), various helpful conversational Artificial Intelligence (AI) systems have been deployed across many applications. When prompted by users, these AI systems…
Large language models (LMs) such as GPT-3 have the surprising ability to do in-context learning, where the model learns to do a downstream task simply by conditioning on a prompt consisting of input-output examples. The LM learns from these…
Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of LLMs encompasses various…
Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier goals of artificial intelligence research: creating an artificial system that can adapt its…
Pre-trained Large Language Models (LLMs) require post-training methods such as supervised fine-tuning (SFT) on instruction-response pairs to enable instruction following. However, this process can potentially harm existing capabilities…
Large Language Models (LLMs), trained on extensive web-scale corpora, have demonstrated remarkable abilities across diverse tasks, especially as they are scaled up. Nevertheless, even state-of-the-art models struggle in certain cases,…
Contextual information at inference time, such as demonstrations, retrieved knowledge, or interaction history, can substantially improve large language models (LLMs) without parameter updates, yet its theoretical role remains poorly…
Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP), owing to their excellent understanding and generation abilities. Remarkably, what further sets these models apart is the massive…
In-context learning (ICL) has emerged as a powerful capability for large language models (LLMs) to adapt to downstream tasks by leveraging a few (demonstration) examples. Despite its effectiveness, the mechanism behind ICL remains…
Recently proposed evaluation benchmarks aim to characterize the effective context length and the forgetting tendencies of large language models (LLMs). However, these benchmarks often rely on simplistic 'needle in a haystack' retrieval or…
Large language models (LLMs) can learn from a few demonstrations provided at inference time. We study this in-context learning phenomenon through the lens of Gaussian Processes (GPs). We build controlled experiments where models observe…
Human cognition is constrained by processing limitations, leading to cognitive overload and inefficiencies in knowledge synthesis and decision-making. Large Language Models (LLMs) present an opportunity for cognitive augmentation, but their…
Large Language Models (LLMs) exhibit positional bias, struggling to utilize information from the middle or end of long contexts. Our study explores LLMs' long-context reasoning by probing their hidden representations. We find that while…
Shortcut learning refers to the phenomenon where models employ simple, non-robust decision rules in practical tasks, which hinders their generalization and robustness. With the rapid development of large language models (LLMs) in recent…
Large language models (LLMs) have been shown to acquire sequence-level planning abilities during training, yet their planning behavior exhibited at inference time often appears short-sighted and inconsistent with these capabilities. We…
We introduce a dynamic benchmarking system for conversational agents that evaluates their performance through a single, simulated, and lengthy user$\leftrightarrow$agent interaction. The interaction is a conversation between the user and…
A standard practice when using large language models is for users to supplement their instruction with an input context containing new information for the model to process. However, models struggle to reliably follow the input context,…
Recent studies have demonstrated that In-Context Learning (ICL), through the use of specific demonstrations, can align Large Language Models (LLMs) with human preferences known as In-Context Alignment (ICA), indicating that models can…
Large language models (LLMs) draw on both contextual information and parametric memory, yet these sources can conflict. Prior studies have largely examined this issue in contextual question answering, implicitly assuming that tasks should…
In-context learning (ICL) has transformed the use of large language models (LLMs) for NLP tasks, enabling few-shot learning by conditioning on labeled examples without finetuning. Despite its effectiveness, ICL is prone to errors,…