Related papers: STaR-GATE: Teaching Language Models to Ask Clarify…
Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These…
When training a model on referential dialogue guessing games, the best model is usually chosen based on its task success. We show that in the popular end-to-end approach, this choice prevents the model from learning to generate…
We explore a method for improving the performance of large language models through self-reflection and reinforcement learning. By incentivizing the model to generate better self-reflections when it answers incorrectly, we demonstrate that a…
Solving temporally-extended tasks is a challenge for most reinforcement learning (RL) algorithms [arXiv:1906.07343]. We investigate the ability of an RL agent to learn to ask natural language questions as a tool to understand its…
Generative question answering (QA) models generate answers to questions either solely based on the parameters of the model (the closed-book setting) or additionally retrieving relevant evidence (the open-book setting). Generative QA models…
Misunderstandings arise not only in interpersonal communication but also between humans and Large Language Models (LLMs). Such discrepancies can make LLMs interpret seemingly unambiguous questions in unexpected ways, yielding incorrect…
One of the exciting capabilities of recent language models for dialog is their ability to independently search for relevant information to ground a given dialog response. However, obtaining training data to teach models how to issue search…
Large language models have recently demonstrated remarkable abilities to self-correct their responses through iterative refinement, often referred to as self-consistency or self-reflection. However, the dynamics of this self-correction…
Humans often specify tasks incompletely, so assistants must know when and how to ask clarifying questions. However, effective clarification remains challenging in software engineering tasks as not all missing information is equally…
The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining. Reformulating tasks as fill-in-the-blanks problems (e.g., cloze tests) is a natural approach for…
The ubiquitous nature of chatbots and their interaction with users generate an enormous amount of data. Can we improve chatbots using this data? A self-feeding chatbot improves itself by asking natural language feedback when a user is…
We introduce GIER (Gap-driven Iterative Enhancement of Responses), a general framework for improving large language model (LLM) outputs through self-reflection and revision based on conceptual quality criteria. Unlike prompting strategies…
Personalization of natural language generation plays a vital role in a large spectrum of tasks, such as explainable recommendation, review summarization and dialog systems. In these tasks, user and item IDs are important identifiers for…
Large language models (LLMs) are increasingly expected to function as collaborative partners, engaging in back-and-forth dialogue to solve complex, ambiguous problems. However, current LLMs often falter in real-world settings, defaulting to…
Previous research into agent communication has shown that a pre-trained guide can speed up the learning process of an imitation learning agent. The guide achieves this by providing the agent with discrete messages in an emerged language…
Question Generation (QG) is a Natural Language Processing (NLP) task that aids advances in Question Answering (QA) and conversational assistants. Existing models focus on generating a question based on a text and possibly the answer to the…
Humans understand language by extracting information (meaning) from sentences, combining it with existing commonsense knowledge, and then performing reasoning to draw conclusions. While large language models (LLMs) such as GPT-3 and ChatGPT…
In this work, we systematically study the problem of personalized text-to-image generation, where the output image is expected to portray information about specific human subjects. E.g., generating images of oneself appearing at imaginative…
Given a textual passage and an answer, humans are able to ask questions with various expressions, but this ability is still challenging for most question generation (QG) systems. Existing solutions mainly focus on the internal knowledge…
Large language models (LLMs) have demonstrated considerable reasoning abilities in various tasks such as mathematics and coding. However, recent studies indicate that even the best models lack true comprehension of their reasoning…