UC Berkeley
Abstract:Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when LLMs are used as reward models. We introduce Meta Policy Optimization (MPO), a framework that addresses these challenges by integrating a meta-reward model that dynamically refines the reward model's prompt throughout training. In MPO, the meta-reward model monitors the evolving training context and continuously adjusts the reward model's prompt to maintain high alignment, providing an adaptive reward signal that resists exploitation by the policy. This meta-learning approach promotes a more stable policy optimization, and greatly reduces the need for manual reward prompt design. It yields performance on par with or better than models guided by extensively hand-crafted reward prompts. Furthermore, we show that MPO maintains its effectiveness across diverse tasks, such as question answering and mathematical reasoning, without requiring specialized reward designs. Beyond standard RLAIF, MPO's meta-learning formulation is readily extensible to higher-level alignment frameworks. Overall, this method addresses theoretical and practical challenges in reward-based RL alignment for LLMs, paving the way for more robust and adaptable alignment strategies. The code and models will be publicly shared.
Abstract:Legal practitioners, particularly those early in their careers, face complex, high-stakes tasks that require adaptive, context-sensitive reasoning. While AI holds promise in supporting legal work, current datasets and models are narrowly focused on isolated subtasks and fail to capture the end-to-end decision-making required in real-world practice. To address this gap, we introduce LawFlow, a dataset of complete end-to-end legal workflows collected from trained law students, grounded in real-world business entity formation scenarios. Unlike prior datasets focused on input-output pairs or linear chains of thought, LawFlow captures dynamic, modular, and iterative reasoning processes that reflect the ambiguity, revision, and client-adaptive strategies of legal practice. Using LawFlow, we compare human and LLM-generated workflows, revealing systematic differences in structure, reasoning flexibility, and plan execution. Human workflows tend to be modular and adaptive, while LLM workflows are more sequential, exhaustive, and less sensitive to downstream implications. Our findings also suggest that legal professionals prefer AI to carry out supportive roles, such as brainstorming, identifying blind spots, and surfacing alternatives, rather than executing complex workflows end-to-end. Building on these findings, we propose a set of design suggestions, rooted in empirical observations, that align AI assistance with human goals of clarity, completeness, creativity, and efficiency, through hybrid planning, adaptive execution, and decision-point support. Our results highlight both the current limitations of LLMs in supporting complex legal workflows and opportunities for developing more collaborative, reasoning-aware legal AI systems. All data and code are available on our project page (https://minnesotanlp.github.io/LawFlow-website/).
Abstract:Generating engaging, accurate short-form videos from scientific papers is challenging due to content complexity and the gap between expert authors and readers. Existing end-to-end methods often suffer from factual inaccuracies and visual artifacts, limiting their utility for scientific dissemination. To address these issues, we propose SciTalk, a novel multi-LLM agentic framework, grounding videos in various sources, such as text, figures, visual styles, and avatars. Inspired by content creators' workflows, SciTalk uses specialized agents for content summarization, visual scene planning, and text and layout editing, and incorporates an iterative feedback mechanism where video agents simulate user roles to give feedback on generated videos from previous iterations and refine generation prompts. Experimental evaluations show that SciTalk outperforms simple prompting methods in generating scientifically accurate and engaging content over the refined loop of video generation. Although preliminary results are still not yet matching human creators' quality, our framework provides valuable insights into the challenges and benefits of feedback-driven video generation. Our code, data, and generated videos will be publicly available.
Abstract:Current reinforcement learning from human feedback (RLHF) pipelines for large language model (LLM) alignment typically assign scalar rewards to sequences, using the final token as a surrogate indicator for the quality of the entire sequence. However, this leads to sparse feedback and suboptimal token-level credit assignment. In this work, we frame reward shaping as an optimization problem focused on token-level credit assignment. We propose a reward-shaping function leveraging explainability methods such as SHAP and LIME to estimate per-token rewards from the reward model. To learn parameters of this shaping function, we employ a bilevel optimization framework that integrates Bayesian Optimization and policy training to handle noise from the token reward estimates. Our experiments show that achieving a better balance of token-level reward attribution leads to performance improvements over baselines on downstream tasks and finds an optimal policy faster during training. Furthermore, we show theoretically that explainability methods that are feature additive attribution functions maintain the optimal policy as the original reward.
Abstract:Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs with human-like discourse structures to enhance long-form text generation. By integrating linguistically grounded discourse frameworks into reinforcement learning, our approach guides models to produce coherent and well-organized outputs. We employ a dense reward scheme within a Proximal Policy Optimization framework, assigning fine-grained, token-level rewards based on the discourse distinctiveness relative to human writing. Two complementary reward models are evaluated: the first improves readability by scoring surface-level textual features to provide explicit structuring, while the second reinforces deeper coherence and rhetorical sophistication by analyzing global discourse patterns through hierarchical discourse motifs, outperforming both standard and RLHF-enhanced models in tasks such as essay generation and long-document summarization. All training data and code will be publicly shared at https://github.com/minnesotanlp/struct_align.
Abstract:Emergent cognitive abilities in large language models (LLMs) have been widely observed, but their nature and underlying mechanisms remain poorly understood. A growing body of research draws on cognitive science to investigate LLM cognition, but standard methodologies and experimen-tal pipelines have not yet been established. To address this gap we develop CognitivEval, a framework for systematically evaluating the artificial cognitive capabilities of LLMs, with a particular emphasis on robustness in response collection. The key features of CognitivEval include: (i) automatic prompt permutations, and (ii) testing that gathers both generations and model probability estimates. Our experiments demonstrate that these features lead to more robust experimental outcomes. Using CognitivEval, we replicate five classic experiments in cognitive science, illustrating the framework's generalizability across various experimental tasks and obtaining a cognitive profile of several state of the art LLMs. CognitivEval will be released publicly to foster broader collaboration within the cognitive science community.
Abstract:Autonomous robotic wiping is an important task in various industries, ranging from industrial manufacturing to sanitization in healthcare. Deep reinforcement learning (Deep RL) has emerged as a promising algorithm, however, it often suffers from a high demand for repetitive reward engineering. Instead of relying on manual tuning, we first analyze the convergence of quality-critical robotic wiping, which requires both high-quality wiping and fast task completion, to show the poor convergence of the problem and propose a new bounded reward formulation to make the problem feasible. Then, we further improve the learning process by proposing a novel visual-language model (VLM) based curriculum, which actively monitors the progress and suggests hyperparameter tuning. We demonstrate that the combined method can find a desirable wiping policy on surfaces with various curvatures, frictions, and waypoints, which cannot be learned with the baseline formulation. The demo of this project can be found at: https://sites.google.com/view/highqualitywiping.
Abstract:Supervised fine-tuning is a standard method for adapting pre-trained large language models (LLMs) to downstream tasks. Quantization has been recently studied as a post-training technique for efficient LLM deployment. To obtain quantized fine-tuned LLMs, conventional pipelines would first fine-tune the pre-trained models, followed by post-training quantization. This often yields suboptimal performance as it fails to leverage the synergy between fine-tuning and quantization. To effectively realize low-bit quantization of weights, activations, and KV caches in LLMs, we propose an algorithm named Rotated Straight-Through-Estimator (RoSTE), which combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy that identifies an effective rotation configuration to reduce activation outliers. We provide theoretical insights on RoSTE by analyzing its prediction error when applied to an overparameterized least square quantized training problem. Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration. Experiments on Pythia and Llama models of different sizes demonstrate the effectiveness of RoSTE. Compared to existing post-SFT quantization baselines, our method consistently achieves superior performances across various tasks and different LLM architectures.
Abstract:Writing is a cognitively demanding task involving continuous decision-making, heavy use of working memory, and frequent switching between multiple activities. Scholarly writing is particularly complex as it requires authors to coordinate many pieces of multiform knowledge. To fully understand writers' cognitive thought process, one should fully decode the end-to-end writing data (from individual ideas to final manuscript) and understand their complex cognitive mechanisms in scholarly writing. We introduce ScholaWrite dataset, the first-of-its-kind keystroke logs of an end-to-end scholarly writing process for complete manuscripts, with thorough annotations of cognitive writing intentions behind each keystroke. Our dataset includes LaTeX-based keystroke data from five preprints with nearly 62K total text changes and annotations across 4 months of paper writing. ScholaWrite shows promising usability and applications (e.g., iterative self-writing) for the future development of AI writing assistants for academic research, which necessitate complex methods beyond LLM prompting. Our experiments clearly demonstrated the importance of collection of end-to-end writing data, rather than the final manuscript, for the development of future writing assistants to support the cognitive thinking process of scientists. Our de-identified dataset, demo, and code repository are available on our project page.
Abstract:Multimodal learning plays a crucial role in enabling machine learning models to fuse and utilize diverse data sources, such as text, images, and audio, to support a variety of downstream tasks. A unified representation across various modalities is particularly important for improving efficiency and performance. Recent binding methods, such as ImageBind (Girdhar et al., 2023), typically use a fixed anchor modality to align multimodal data in the anchor modal embedding space. In this paper, we mathematically analyze the fixed anchor binding methods and uncover notable limitations: (1) over-reliance on the choice of the anchor modality, (2) failure to capture intra-modal information, and (3) failure to account for inter-modal correlation among non-anchored modalities. To address these limitations, we propose CentroBind, a simple yet powerful approach that eliminates the need for a fixed anchor; instead, it employs dynamically adjustable centroid-based anchors generated from all available modalities, resulting in a balanced and rich representation space. We theoretically demonstrate that our method captures three crucial properties of multimodal learning: intra-modal learning, inter-modal learning, and multimodal alignment, while also constructing a robust unified representation across all modalities. Our experiments on both synthetic and real-world datasets demonstrate the superiority of the proposed method, showing that dynamic anchor methods outperform all fixed anchor binding methods as the former captures more nuanced multimodal interactions.