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 …
Self-rewarding language models
We posit that to achieve superhuman agents, future models require superhuman feedback
in order to provide an adequate training signal. Current approaches commonly train reward …
in order to provide an adequate training signal. Current approaches commonly train reward …
Llm-based nlg evaluation: Current status and challenges
Evaluating natural language generation (NLG) is a vital but challenging problem in artificial
intelligence. Traditional evaluation metrics mainly capturing content (eg n-gram) overlap …
intelligence. Traditional evaluation metrics mainly capturing content (eg n-gram) overlap …
Evaluating large language models at evaluating instruction following
As research in large language models (LLMs) continues to accelerate, LLM-based
evaluation has emerged as a scalable and cost-effective alternative to human evaluations …
evaluation has emerged as a scalable and cost-effective alternative to human evaluations …
Self-discover: Large language models self-compose reasoning structures
We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-
intrinsic reasoning structures to tackle complex reasoning problems that are challenging for …
intrinsic reasoning structures to tackle complex reasoning problems that are challenging for …
A comprehensive survey on instruction following
Task semantics can be expressed by a set of input-output examples or a piece of textual
instruction. Conventional machine learning approaches for natural language processing …
instruction. Conventional machine learning approaches for natural language processing …
Beyond chatbots: Explorellm for structured thoughts and personalized model responses
Large language model (LLM) powered chatbots are primarily text-based today, and impose
a large interactional cognitive load, especially for exploratory or sensemaking tasks such as …
a large interactional cognitive load, especially for exploratory or sensemaking tasks such as …
Topologies of reasoning: Demystifying chains, trees, and graphs of thoughts
M Besta, F Memedi, Z Zhang, R Gerstenberger… - arXiv preprint arXiv …, 2024 - arxiv.org
The field of natural language processing (NLP) has witnessed significant progress in recent
years, with a notable focus on improving large language models'(LLM) performance through …
years, with a notable focus on improving large language models'(LLM) performance through …
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 …
Concept--An Evaluation Protocol on Conversation Recommender Systems with System-and User-centric Factors
The conversational recommendation system (CRS) has been criticized regarding its user
experience in real-world scenarios, despite recent significant progress achieved in …
experience in real-world scenarios, despite recent significant progress achieved in …