Related papers: Scaling Human Judgment in Community Notes with LLM…

As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on human or LLM annotated datasets, are limited by their…

Pairwise preference data have played an important role in the alignment of large language models (LLMs). Each sample of such data consists of a prompt, two different responses to the prompt, and a binary label indicating which of the two…

The increasing volume of research paper submissions poses a significant challenge to the traditional academic peer-review system, leading to an overwhelming workload for reviewers. This study explores the potential of integrating Large…

The release note is a crucial document outlining changes in new software versions. Yet, many developers view the process of writing software release notes as a tedious and dreadful task. Consequently, numerous tools have been developed by…

Reinforcement Learning from Human feedback (RLHF) has become a powerful tool to fine-tune or train agentic machine learning models. Similar to how humans interact in social contexts, we can use many types of feedback to communicate our…

Annotating large datasets can be challenging. However, crowd-sourcing is often expensive and can lack quality, especially for non-trivial tasks. We propose a method of using LLMs as few-shot learners for annotating data in a complex natural…

Social media platforms face increasing scrutiny over the rapid spread of misinformation. In response, many have adopted community-based content moderation systems, including Community Notes (formerly Birdwatch) on X (formerly Twitter),…

Large Language Models (LLMs) are extensively used in text generation tasks. These generative capabilities bring us to a point where LLMs could potentially provide useful insights in policy making or agency operations. In this paper, we…

Recommender systems utilizing explicit feedback have witnessed significant advancements and widespread applications over the past years. However, generating recommendations in few-shot scenarios remains a persistent challenge. Recently,…

As Large Language Models (LLMs) continue to evolve, evaluating them remains a persistent challenge. Many recent evaluations use LLMs as judges to score outputs from other LLMs, often relying on a single large model like GPT-4o. However,…

Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating remarkable potential in tackling real-world challenges. Despite its promising prospects, this methodology has encountered with issues and challenges,…

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However,…

As platforms increasingly scale down professional fact-checking, community-based alternatives are promoted as more transparent and democratic. The main substitute being proposed is community-based contextualization, most notably Community…

Humans and large language models (LLMs) now co-produce and co-consume the web's shared knowledge archives. Such human-AI collective knowledge ecosystems contain feedback loops with both benefits (e.g., faster growth, easier learning) and…

Modern large language models (LLMs) are optimized for human-aligned responses using Reinforcement Learning from Human Feedback (RLHF). However, existing RLHF approaches assume a universal preference model and fail to account for individual…

Relevance evaluation plays a crucial role in personalized search systems to ensure that search results align with a user's queries and intent. While human annotation is the traditional method for relevance evaluation, its high cost and long…

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

In this study, we investigate the enhancement of the GPT Neo 125M performance in Community Question Answering (CQA) with a focus on programming, through the integration of Reinforcement Learning from Human Feedback (RLHF) and the…

Learning from human feedback has shown success in aligning large, pretrained models with human values. Prior works have mostly focused on learning from high-level labels, such as preferences between pairs of model outputs. On the other…

Recent advancements in Large Language Models (LLMs) have garnered wide attention and led to successful products such as ChatGPT and GPT-4. Their proficiency in adhering to instructions and delivering harmless, helpful, and honest (3H)…