Related papers: Privately Aligning Language Models with Reinforcem…
Large language models (LLMs) can transform education, but their optimization for direct question-answering often undermines effective pedagogy which requires strategically withholding answers. To mitigate this, we propose an online…
Reinforcement Learning from Human Feedback (RLHF) is the standard for aligning Large Language Models (LLMs), yet recent progress has moved beyond canonical text-based methods. This survey synthesizes the new frontier of alignment research…
We study the problem of multi-agent reinforcement learning (multi-agent RL) with differential privacy (DP) constraints. This is well-motivated by various real-world applications involving sensitive data, where it is critical to protect…
With the recent remarkable advancement of large language models (LLMs), there has been a growing interest in utilizing them in the domains with highly sensitive data that lies outside their training data. For this purpose,…
Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversational models like GPT-4, ChatGPT, and Llama 2. A core challenge…
The remarkable ability of language models (LMs) has also brought challenges at the interface of AI and security. A critical challenge pertains to how much information these models retain and leak about the training data. This is…
Large Language Models (LLMs) have achieved remarkable progress in natural language understanding, reasoning, and autonomous decision-making. However, these advancements have also come with significant privacy concerns. While significant…
To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the…
We present the first theoretical guarantees for differentially private online reinforcement learning (RL) with general function approximation, extending beyond prior work restricted to tabular and linear settings. Our approach combines a…
Learning from preference-based feedback has recently gained considerable traction as a promising approach to align generative models with human interests. Instead of relying on numerical rewards, the generative models are trained using…
Large scale adoption of large language models has introduced a new era of convenient knowledge transfer for a slew of natural language processing tasks. However, these models also run the risk of undermining user trust by exposing unwanted…
Deep Reinforcement Learning is widely used for aligning Large Language Models (LLM) with human preference. However, the conventional reward modelling is predominantly dependent on human annotations provided by a select cohort of…
Deep learning (DL) models for natural language processing (NLP) tasks often handle private data, demanding protection against breaches and disclosures. Data protection laws, such as the European Union's General Data Protection Regulation…
In the era of increasing privacy concerns and demand for personalized experiences, traditional Reinforcement Learning with Human Feedback (RLHF) frameworks face significant challenges due to their reliance on centralized data. We introduce…
Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning Large Language Models (LLMs) for text generation. In particular, recent LLMs such as ChatGPT and GPT-4 can engage in fluent conversations with users after…
Ensuring alignment with human preferences is a crucial characteristic of large language models (LLMs). Presently, the primary alignment methods, RLHF and DPO, require extensive human annotation, which is expensive despite their efficacy.…
Learning from human feedback is a prominent technique to align the output of large language models (LLMs) with human expectations. Reinforcement learning from human feedback (RLHF) leverages human preference signals that are in the form of…
In-context learning (ICL) enables Large Language Models (LLMs) to adapt to new tasks with only a small set of examples at inference time, thereby avoiding task-specific fine-tuning. However, in-context examples may contain privacy-sensitive…
Aligning Large Language Models (LLMs) with human values and away from undesirable behaviors (such as hallucination) has become increasingly important. Recently, steering LLMs towards a desired behavior via activation editing has emerged as…
Natural Language Processing (NLP) techniques can be applied to help with the diagnosis of medical conditions such as depression, using a collection of a person's utterances. Depression is a serious medical illness that can have adverse…