Related papers: Self-Correction as Feedback Control: Error Dynamic…

Fine-tuning a pre-trained model (such as BERT, ALBERT, RoBERTa, T5, GPT, etc.) has proven to be one of the most promising paradigms in recent NLP research. However, numerous recent works indicate that fine-tuning suffers from the…

A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution. Existing Self-Consistency techniques always generate a…

Multi-agent large language model (LLM) systems often rely on a controller to coordinate a pool of heterogeneous models, yet existing controllers are typically limited to one-shot routing: they select a model once and return its output…

Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this…

Reinforcement learning with verifiable rewards (RLVR) scales the reasoning ability of large language models (LLMs) but remains bottlenecked by limited labeled samples for continued data scaling. Reinforcement learning with intrinsic rewards…

The growing scale and complexity of safety-critical control systems underscore the need to evolve current control architectures aiming for the unparalleled performances achievable through state-of-the-art optimization and machine learning…

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…

Automated assistants for Grammatical Error Correction are now embedded in educational platforms serving millions of learners, yet three critical gaps remain in this domain: (1) latest-generation Large Language Models (LLMs) lack…

Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more…

Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by…

We demonstrate an approach for LLMs to critique their \emph{own} answers with the goal of enhancing their performance that leads to significant improvements over established planning benchmarks. Despite the findings of earlier research that…

Reasoning about failures is crucial for building reliable and trustworthy robotic systems. Prior approaches either treat failure reasoning as a closed-set classification problem or assume access to ample human annotations. Failures in the…

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…

Recently, there has been a surge in interest in safe and robust techniques within reinforcement learning (RL). Current notions of risk in RL fail to capture the potential for systemic failures such as abrupt stoppages from system failures…

We audit alignment-induced shifts in residual-stream activations of three open-weight instruction-tuned LLMs (Llama-3.1-8B-Instruct, Gemma-2-9B-it, Qwen-2.5-7B-Instruct) using the effective rank of the alignment modification matrix on…

Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…

Large language models have shown remarkable aptitude in code generation, but still struggle to perform complex tasks. Self-repair -- in which the model debugs and repairs its own code -- has recently become a popular way to boost…

End-to-end models for autonomous driving hold the promise of learning complex behaviors directly from sensor data, but face critical challenges in safety and handling long-tail events. Reinforcement Learning (RL) offers a promising path to…

Large language models (LLMs) are increasingly deployed as "agents" for decision-making (DM) in interactive and dynamic environments. Yet, since they were not originally designed for DM, recent studies show that LLMs can struggle even in…

In order to obviate the requirement of drift dynamics in adaptive dynamic programming (ADP), integral reinforcement learning (IRL) has been proposed as an alternate formulation of Bellman equation.However control coupling dynamics is still…