Yunxuan Li

Hyung Won Chung, Le Hou, Shayne Longpre et al. · cmu, deepmind

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1) scaling the number of tasks, (2) scaling the model size, and (3) finetuning on chain-of-thought data. We find that instruction finetuning with the above aspects dramatically improves performance on a variety of model classes (PaLM, T5, U-PaLM), prompting setups (zero-shot, few-shot, CoT), and evaluation benchmarks (MMLU, BBH, TyDiQA, MGSM, open-ended generation). For instance, Flan-PaLM 540B instruction-finetuned on 1.8K tasks outperforms PALM 540B by a large margin (+9.4% on average). Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints, which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language models.

Kaiwen Wang, Rahul Kidambi, Ryan Sullivan et al.

Reward-based finetuning is crucial for aligning language policies with intended behaviors (e.g., creativity and safety). A key challenge is to develop steerable language models that trade-off multiple (conflicting) objectives in a flexible and efficient manner. This paper presents Conditional Language Policy (CLP), a general framework for finetuning language models on multiple objectives. Building on techniques from multi-task training and parameter-efficient finetuning, CLP learn steerable models that effectively trade-off conflicting objectives at inference time. Notably, this does not require training or maintaining multiple models to achieve different trade-offs between the objectives. Through extensive experiments and ablations on two summarization datasets, we show that CLP learns steerable language models that outperform and Pareto-dominate the existing approaches for multi-objective finetuning.

Ziqi Wang, Le Hou, Tianjian Lu et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. However, the inherent open-ended nature of these tasks implies that there is always room for improvement in the quality of model responses. To address this challenge, various approaches have been proposed to enhance the performance of LLMs. There has been a growing focus on enabling LLMs to self-improve their response quality, thereby reducing the reliance on extensive human annotation efforts for collecting diverse and high-quality training data. Recently, prompting-based methods have been widely explored among self-improvement methods owing to their effectiveness, efficiency, and convenience. However, those methods usually require explicitly and thoroughly written rubrics as inputs to LLMs. It is expensive and challenging to manually derive and provide all necessary rubrics with a real-world complex goal for improvement (e.g., being more helpful and less harmful). To this end, we propose an ImPlicit Self-ImprovemenT (PIT) framework that implicitly learns the improvement goal from human preference data. PIT only requires preference data that are used to train reward models without extra human efforts. Specifically, we reformulate the training objective of reinforcement learning from human feedback (RLHF) -- instead of maximizing response quality for a given input, we maximize the quality gap of the response conditioned on a reference response. In this way, PIT is implicitly trained with the improvement goal of better aligning with human preferences. Experiments on two real-world datasets and one synthetic dataset show that our method significantly outperforms prompting-based methods.

Lei Fan, Mingfu Liang, Yunxuan Li et al.

Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions. Recent approaches favor learning policies from simulated or collected data, wherein appropriate actions are more frequently selected when the recognition is accurate. However, most recognition modules are developed under the closed-world assumption, which makes them ill-equipped to handle unexpected inputs, such as the absence of the target object in the current observation. To address this issue, we propose treating active recognition as a sequential evidence-gathering process, providing by-step uncertainty quantification and reliable prediction under the evidence combination theory. Additionally, the reward function developed in this paper effectively characterizes the merit of actions when operating in open-world environments. To evaluate the performance, we collect a dataset from an indoor simulator, encompassing various recognition challenges such as distance, occlusion levels, and visibility. Through a series of experiments on recognition and robustness analysis, we demonstrate the necessity of introducing uncertainties to active recognition and the superior performance of the proposed method.

Justin B. Hart, Awwab A. Azam, Thomas Li et al.

We develop a representability-aware and interpolable neural network (NN) framework for predicting two-particle reduced density matrices (2-RDMs). The NN incorporates a subset of representability conditions through its architecture and loss function, and can operate on different momentum meshes, enabling evaluating the representability conditions across multiple meshes, which we call interpolated representability condition. The framework can be used either to predict 2-RDMs on large momentum meshes by interpolating exact results from small meshes, or as a variational 2-RDM ansatz optimized by energy minimization on arbitrary meshes. We apply this approach to the fractional Chern insulator in the one-band projected model of twisted bilayer MoTe$_2$ at twist angle $3.89^\circ$ and hole filling $2/3$. Trained on exact-diagonalization (ED) 2-RDMs from meshes with $12$ or $18$ momentum points using six different NN architectures, the best NN is the residual multilayer perceptron, which predicts the $6\times6$ 2-RDM with $97.07\%-98.18\%$ accuracy relative to the ED 2-RDM but predicts an energy $77.353$ meV above ED ground-state energy. We then variationally optimize the NN on several meshes including $6\times6$, predicting a $6\times 6$ energy of just $0.104$ meV below ED while maintaining $98.94\%-98.96\%$ accuracy. Compared with the conventional boundary-point semidefinite programming, which gives an energy $5.560$ meV below ED with $96.40\%-98.94\%$ accuracy, the NN achieves a more accurate energy and similar accuracy while using only less than 1/20 as many parameters. Eventually, we add a symmetric mesh of $48$ momentum points to the variational optimization of the NN, and provide a prediction of the many-body ground-state energy and the many-body quantum metric on that mesh.

Zihan Wang, Yunxuan Li, Yuexin Wu et al.

Process supervision, using a trained verifier to evaluate the intermediate steps generated by a reasoner, has demonstrated significant improvements in multi-step problem solving. In this paper, to avoid the expensive effort of human annotation on the verifier training data, we introduce Model-induced Process Supervision (MiPS), a novel method for automating data curation. MiPS annotates an intermediate step by sampling completions of this solution through the reasoning model, and obtaining an accuracy defined as the proportion of correct completions. Inaccuracies of the reasoner would cause MiPS underestimating the accuracy of intermediate steps, therefore, we suggest and empirically show that verification focusing on high predicted scores of the verifier shall be preferred over that of low predicted scores, contrary to prior observations on human curated data. Our approach significantly improves the performance of PaLM 2 on math and coding tasks (accuracy +0.67% on GSM8K, +4.16% on MATH, +0.92% on MBPP compared with an output supervision trained verifier). Additionally, our study demonstrates that the verifier exhibits strong generalization ability across different reasoning models.

Raghav Gupta, Ryan Sullivan, Yunxuan Li et al. · deepmind

Multi-objective preference alignment of large language models (LLMs) is critical for developing AI systems that are more configurable, personalizable, helpful, and safe. However, optimizing model outputs to satisfy diverse objectives with variable weights at inference time for truly personalized models presents a significant challenge. Existing approaches are either computationally expensive to train or do not sufficiently steer model behaviors. This paper introduces the Multi-Objective Online DPO (MO-ODPO) algorithm, designed to robustly and efficiently align model behaviors with multiple, potentially conflicting human preferences. Our approach incorporates a prompt conditioning mechanism, allowing us to train a single preference-conditional policy, that can adapt to new preference combinations at inference. Experiments on two popular benchmarks show that MO-ODPO Pareto-dominates existing baselines while providing excellent inference-time steerability between diverse objectives.

Xiao Hu, Yuansheng Lian, Ke Zhang et al.

This study proposes an interpretable prediction framework with literature-informed fine-tuned (LIFT) LLMs for truck driving risk prediction. The framework integrates an LLM-driven Inference Core that predicts and explains truck driving risk, a Literature Processing Pipeline that filters and summarizes domain-specific literature into a literature knowledge base, and a Result Evaluator that evaluates the prediction performance as well as the interpretability of the LIFT LLM. After fine-tuning on a real-world truck driving risk dataset, the LIFT LLM achieved accurate risk prediction, outperforming benchmark models by 26.7% in recall and 10.1% in F1-score. Furthermore, guided by the literature knowledge base automatically constructed from 299 domain papers, the LIFT LLM produced variable importance ranking consistent with that derived from the benchmark model, while demonstrating robustness in interpretation results to various data sampling conditions. The LIFT LLM also identified potential risky scenarios by detecting key combination of variables in truck driving risk, which were verified by PERMANOVA tests. Finally, we demonstrated the contribution of the literature knowledge base and the fine-tuning process in the interpretability of the LIFT LLM, and discussed the potential of the LIFT LLM in data-driven knowledge discovery.

Yuanshuai Li, Yuping Yan, Junfeng Tang et al.

Multimodal Large Language Models (MLLMs) have significantly improved the performance of various tasks, but continue to suffer from visual hallucinations, a critical issue where generated responses contradict visual evidence. While Direct Preference Optimization(DPO) is widely used for alignment, its application to MLLMs often fails to capture fine-grained semantic differences and encourages shortcut learning. To address these challenges, we propose Semantic Curriculum Preference Optimization (SCPO), a novel framework for MLLM alignment. SCPO employs a progressive, easy-to-hard curriculum built upon our Semantic Curriculum Preference Pairs dataset, which provides fine-grained semantic contrasts sorted by difficulty. This curriculum is trained with a dynamic reference model and a novel symmetric, bidirectional objective to facilitate simultaneous learning from both textual and visual preferences. To our knowledge, SCPO is the first framework to unify semantics, symmetry, and curriculum for MLLMs alignment, effectively mitigating visual hallucinations. Extensive experiments on LLaVA models across various scales and versions validate that SCPO demonstrates superior performance compared to baseline models on multiple hallucination benchmarks, reducing the hallucination rate by up to 62.9%. Moreover, evaluations on generalized benchmarks show that SCPO improves factuality while preserving general capabilities, with its performance remaining stable across general vision-language benchmarks.

Yunxuan Li, Yibing Du, Jiageng Zhang et al.

Multi-agent debate has proven effective in improving large language models quality for reasoning and factuality tasks. While various role-playing strategies in multi-agent debates have been explored, in terms of the communication among agents, existing approaches adopt a brute force algorithm -- each agent can communicate with all other agents. In this paper, we systematically investigate the effect of communication connectivity in multi-agent systems. Our experiments on GPT and Mistral models reveal that multi-agent debates leveraging sparse communication topology can achieve comparable or superior performance while significantly reducing computational costs. Furthermore, we extend the multi-agent debate framework to multimodal reasoning and alignment labeling tasks, showcasing its broad applicability and effectiveness. Our findings underscore the importance of communication connectivity on enhancing the efficiency and effectiveness of the "society of minds" approach.

Liangchen Luo, Yinxiao Liu, Rosanne Liu et al.

Complex multi-step reasoning tasks, such as solving mathematical problems or generating code, remain a significant hurdle for even the most advanced large language models (LLMs). Verifying LLM outputs with an Outcome Reward Model (ORM) is a standard inference-time technique aimed at enhancing the reasoning performance of LLMs. However, this still proves insufficient for reasoning tasks with a lengthy or multi-hop reasoning chain, where the intermediate outcomes are neither properly rewarded nor penalized. Process supervision addresses this limitation by assigning intermediate rewards during the reasoning process. To date, the methods used to collect process supervision data have relied on either human annotation or per-step Monte Carlo estimation, both prohibitively expensive to scale, thus hindering the broad application of this technique. In response to this challenge, we propose a novel divide-and-conquer style Monte Carlo Tree Search (MCTS) algorithm named \textit{OmegaPRM} for the efficient collection of high-quality process supervision data. This algorithm swiftly identifies the first error in the Chain of Thought (CoT) with binary search and balances the positive and negative examples, thereby ensuring both efficiency and quality. As a result, we are able to collect over 1.5 million process supervision annotations to train Process Reward Models (PRMs). This fully automated process supervision alongside the weighted self-consistency algorithm is able to enhance LLMs' math reasoning performances. We improved the success rates of the instruction-tuned Gemini Pro model from 51\% to 69.4\% on MATH500 and from 86.4\% to 93.6\% on GSM8K. Similarly, we boosted the success rates of Gemma2 27B from 42.3\% to 58.2\% on MATH500 and from 74.0\% to 92.2\% on GSM8K. The entire process operates without any human intervention or supervision, making our method both financially and ...

Gemini Team, Rohan Anil, Sebastian Borgeaud et al.

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of the Gemini family in cross-modal reasoning and language understanding will enable a wide variety of use cases. We discuss our approach toward post-training and deploying Gemini models responsibly to users through services including Gemini, Gemini Advanced, Google AI Studio, and Cloud Vertex AI.

Sheng Shen, Le Hou, Yanqi Zhou et al.

Sparse Mixture-of-Experts (MoE) is a neural architecture design that can be utilized to add learnable parameters to Large Language Models (LLMs) without increasing inference cost. Instruction tuning is a technique for training LLMs to follow instructions. We advocate combining these two approaches, as we find that MoE models benefit more from instruction tuning than dense models. In particular, we conduct empirical studies across three experimental setups: (i) Direct finetuning on individual downstream tasks devoid of instruction tuning; (ii) Instructiontuning followed by in-context few-shot or zero-shot generalization on downstream tasks; and (iii) Instruction tuning supplemented by further finetuning on individual downstream tasks. In the first scenario, MoE models overall underperform dense models of identical computational capacity. This narrative, however, dramatically changes with the introduction of instruction tuning (second and third scenario), used independently or in conjunction with task-specific finetuning. Our most powerful model, FLAN-MOE-32B, surpasses the performance of FLAN-PALM-62B on four benchmark tasks, while using only a third of the FLOPs. The advancements embodied byFLAN-MOE inspire a reevaluation of the design principles of large-scale, high-performance language models in the framework of task-agnostic learning.