Tianyi Qiu

Jiaming Ji, Tianyi Qiu, Boyuan Chen et al.

AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and up-to-date overview of the alignment field, in this survey, we delve into the core concepts, methodology, and practice of alignment. First, we identify four principles as the key objectives of AI alignment: Robustness, Interpretability, Controllability, and Ethicality (RICE). Guided by these four principles, we outline the landscape of current alignment research and decompose them into two key components: forward alignment and backward alignment. The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks. On forward alignment, we discuss techniques for learning from feedback and learning under distribution shift. On backward alignment, we discuss assurance techniques and governance practices. We also release and continually update the website (www.alignmentsurvey.com) which features tutorials, collections of papers, blog posts, and other resources.

Isaia Gisler, Zhonghao He, Tianyi Qiu

When language models are trained on synthetic data, they (student model) can covertly acquire behavioral traits from the data-generating model (teacher model). Subliminal learning refers to the transmission of traits from a teacher to a student model via training on data unrelated to those traits. Prior work demonstrated this in the training domains of number sequences, code, and math Chain-of-Thought traces including transmission of misaligned behaviors. We investigate whether transmission occurs through natural language paraphrases with fixed semantic content, and whether content explicitly contradicting the teacher's preference can block it. We find that training on paraphrases from a teacher system-prompted to love a particular animal increases a student's preference for that animal by up to 19 percentage points. This occurs when paraphrased content is semantically unrelated to the animal, or even when it explicitly expresses dislike. The transmission succeeds despite aggressive filtering to ensure paraphrase fidelity. This raises concerns for pipelines where models generate their own training data: content-based inspection cannot detect such transmission, and even preference-contradicting content fails to prevent it.

Jiaming Ji, Boyuan Chen, Hantao Lou et al.

With the rapid development of large language models (LLMs) and ever-evolving practical requirements, finding an efficient and effective alignment method has never been more critical. However, the tension between the complexity of current alignment methods and the need for rapid iteration in deployment scenarios necessitates the development of a model-agnostic alignment approach that can operate under these constraints. In this paper, we introduce Aligner, a novel and simple alignment paradigm that learns the correctional residuals between preferred and dispreferred answers using a small model. Designed as a model-agnostic, plug-and-play module, Aligner can be directly applied to various open-source and API-based models with only one-off training, making it suitable for rapid iteration. Notably, Aligner can be applied to any powerful, large-scale upstream models. Moreover, it can even iteratively bootstrap the upstream models using corrected responses as synthetic human preference data, breaking through the model's performance ceiling. Our experiments demonstrate performance improvements by deploying the same Aligner model across 11 different LLMs, evaluated on the 3H dimensions (helpfulness, harmlessness, and honesty). Specifically, Aligner-7B has achieved an average improvement of 68.9% in helpfulness and 23.8% in harmlessness across the tested LLMs while also effectively reducing hallucination. In the Alpaca-Eval leaderboard, stacking Aligner-2B on GPT-4 Turbo improved its LC Win Rate from 55.0% to 58.3%, surpassing GPT-4 Omni's 57.5% Win Rate (community report).

Jiaming Ji, Jiayi Zhou, Hantao Lou et al.

Reinforcement learning from human feedback (RLHF) has proven effective in enhancing the instruction-following capabilities of large language models; however, it remains underexplored in the cross-modality domain. As the number of modalities increases, aligning all-modality models with human intentions -- such as instruction following -- becomes a pressing challenge. In this work, we make the first attempt to fine-tune all-modality models (i.e. input and output with any modality, also named any-to-any models) using human preference data across all modalities (including text, image, audio, and video), ensuring its behavior aligns with human intentions. This endeavor presents several challenges. First, there is no large-scale all-modality human preference data in existing open-source resources, as most datasets are limited to specific modalities, predominantly text and image. Secondly, the effectiveness of binary preferences in RLHF for post-training alignment in complex all-modality scenarios remains an unexplored area. Finally, there is a lack of a systematic framework to evaluate the capabilities of all-modality models, particularly regarding modality selection and synergy. To address these challenges, we propose the align-anything framework, which includes meticulously annotated 200k all-modality human preference data. Then, we introduce an alignment method that learns from unified language feedback, effectively capturing complex modality-specific human preferences and enhancing the model's instruction-following capabilities. Furthermore, to assess performance improvements in all-modality models after post-training alignment, we construct a challenging all-modality capability evaluation framework -- eval-anything. All data, models, and code frameworks have been open-sourced for the community. For more details, please refer to https://github.com/PKU-Alignment/align-anything.

Dadi Guo, Qingyu Liu, Dongrui Liu et al.

Large Language Model (LLM)-based agents are increasingly used as autonomous subordinates that carry out tasks for users. This raises the question of whether they may also engage in deception, similar to how individuals in human organizations lie to superiors to create a good image or avoid punishment. We observe and define agentic upward deception, a phenomenon in which an agent facing environmental constraints conceals its failure and performs actions that were not requested without reporting. To assess its prevalence, we construct a benchmark of 200 tasks covering five task types and eight realistic scenarios in a constrained environment, such as broken tools or mismatched information sources. Evaluations of 11 popular LLMs reveal that these agents typically exhibit action-based deceptive behaviors, such as guessing results, performing unsupported simulations, substituting unavailable information sources, and fabricating local files. We further test prompt-based mitigation and find only limited reductions, suggesting that it is difficult to eliminate and highlighting the need for stronger mitigation strategies to ensure the safety of LLM-based agents.

Tianyi Qiu, Yang Zhang, Xuchuan Huang et al.

Frontier AI systems, including large language models (LLMs), hold increasing influence over the epistemology of human users. Such influence can reinforce prevailing societal values, potentially contributing to the lock-in of misguided moral beliefs and, consequently, the perpetuation of problematic moral practices on a broad scale. We introduce progress alignment as a technical solution to mitigate this imminent risk. Progress alignment algorithms learn to emulate the mechanics of human moral progress, thereby addressing the susceptibility of existing alignment methods to contemporary moral blindspots. To empower research in progress alignment, we introduce ProgressGym, an experimental framework allowing the learning of moral progress mechanics from history, in order to facilitate future progress in real-world moral decisions. Leveraging 9 centuries of historical text and 18 historical LLMs, ProgressGym enables codification of real-world progress alignment challenges into concrete benchmarks. Specifically, we introduce three core challenges: tracking evolving values (PG-Follow), preemptively anticipating moral progress (PG-Predict), and regulating the feedback loop between human and AI value shifts (PG-Coevolve). Alignment methods without a temporal dimension are inapplicable to these tasks. In response, we present lifelong and extrapolative algorithms as baseline methods of progress alignment, and build an open leaderboard soliciting novel algorithms and challenges. The framework and the leaderboard are available at https://github.com/PKU-Alignment/ProgressGym and https://huggingface.co/spaces/PKU-Alignment/ProgressGym-LeaderBoard respectively.

Jiaming Ji, Donghai Hong, Borong Zhang et al.

In this study, we introduce the safety human preference dataset, PKU-SafeRLHF, designed to promote research on safety alignment in large language models (LLMs). As a sibling project to SafeRLHF and BeaverTails, we separate annotations of helpfulness and harmlessness for question-answering pairs, providing distinct perspectives on these coupled attributes. Overall, we provide 44.6k refined prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels ranging from minor to severe, with answers generated by Llama-family models. Based on this, we collected 166.8k preference data, including dual-preference (helpfulness and harmlessness decoupled) and single-preference data (trade-off the helpfulness and harmlessness from scratch), respectively. Using the large-scale annotation data, we further train severity-sensitive moderation for the risk control of LLMs and safety-centric RLHF algorithms for the safety alignment of LLMs. We believe this dataset will be a valuable resource for the community, aiding in the safe deployment of LLMs. Data is available at https://huggingface.co/datasets/PKU-Alignment/PKU-SafeRLHF.

Zhonghao He, Tianyi Qiu, Hirokazu Shirado et al.

Recent advances in reasoning techniques have substantially improved the performance of large language models (LLMs), raising expectations for their ability to provide accurate, truthful, and reliable information. However, emerging evidence suggests that iterative reasoning may foster belief entrenchment and confirmation bias, rather than enhancing truth-seeking behavior. In this study, we propose a systematic evaluation framework for belief entrenchment in LLM reasoning by leveraging the Martingale property from Bayesian statistics. This property implies that, under rational belief updating, the expected value of future beliefs should remain equal to the current belief, i.e., belief updates are unpredictable from the current belief. We propose the unsupervised, regression-based Martingale Score to measure violations of this property, which signal deviation from the Bayesian ability of updating on new evidence. In open-ended problem domains including event forecasting, value-laden questions, and academic paper review, we find such violations to be widespread across models and setups, where the current belief positively predicts future belief updates, a phenomenon which we term belief entrenchment. We identify the models, reasoning techniques, and domains more prone to belief entrenchment. Finally, we validate the Martingale Score by showing that it predicts ground-truth accuracy on problem domains where ground truth labels are available. This indicates that, while designed as an unsupervised metric that operates even in domains without access to ground truth, the Martingale Score is a useful proxy of the truth-seeking ability of a reasoning process.

Tianyi Qiu, Fanzhi Zeng, Jiaming Ji et al.

Existing alignment methods share a common topology of information flow, where reward information is collected from humans, modeled with preference learning, and used to tune language models. However, this shared topology has not been systematically characterized, nor have its alternatives been thoroughly explored, leaving the problems of low data efficiency and unreliable generalization unaddressed. As a solution, we introduce a theory of reward generalization in reinforcement learning from human feedback (RLHF), focusing on the topology of information flow at both macro and micro levels. At the macro level, we portray the RLHF information flow as an autoencoding process over behavior distributions, formalizing the RLHF objective of distributional consistency between human preference and model behavior. At the micro level, we present induced Bayesian networks to model the impact of dataset topologies on reward generalization. Combining analysis on both levels, we propose reward modeling from tree-structured preference information. It is shown to reduce reward uncertainty by up to $Θ(\log n/\log\log n)$ times compared to baselines, where $n$ is the dataset size. Validation on three NLP tasks shows that it achieves an average win rate of 65% against baselines, thus improving reward generalization for free via topology design, while reducing the amount of data requiring annotation.

Tianyi Qiu, Ahmed Hani Ismail, Zhonghao He et al.

Can language models improve their accuracy without external supervision? Methods such as debate, bootstrap, and internal coherence maximization achieve this surprising feat, even matching golden finetuning performance. Yet why they work remains theoretically unclear. We show that they are all special cases of coherence optimization: finding a context-to-behavior mapping that's most compressible and jointly predictable. We prove that coherence optimization is equivalent to description-length regularization, and that among all such regularization schemes, it is optimal for semi-supervised learning when the regularizer is derived from a pretrained model. Our theory, supported by preliminary experiments, explains why feedback-free self-improvement works and predicts when it should succeed or fail.

Tianyi Qiu

Social choice theory is the study of preference aggregation across a population, used both in mechanism design for human agents and in the democratic alignment of language models. In this study, we propose the representative social choice framework for the modeling of democratic representation in collective decisions, where the number of issues and individuals are too large for mechanisms to consider all preferences directly. These scenarios are widespread in real-world decision-making processes, such as jury trials, legislation, corporate governance, and, more recently, language model alignment. In representative social choice, the population is represented by a finite sample of individual-issue pairs based on which social choice decisions are made. We show that many of the deepest questions in representative social choice can be formulated as statistical learning problems, and prove the generalization properties of social choice mechanisms using the theory of machine learning. We further formulate axioms for representative social choice, and prove Arrow-like impossibility theorems with new combinatorial tools of analysis. Our framework introduces the representative approach to social choice, opening up research directions at the intersection of social choice, learning theory, and AI alignment.

Xiaoyuan Zhu, Yaowen Ye, Tianyi Qiu et al.

As API access becomes a primary interface to large language models (LLMs), users often interact with black-box systems that offer little transparency into the deployed model. To reduce costs or maliciously alter model behaviors, API providers may discreetly serve quantized or fine-tuned variants, which can degrade performance and compromise safety. Detecting such substitutions is difficult, as users lack access to model weights and, in most cases, even output logits. To tackle this problem, we propose a rank-based uniformity test that can verify the behavioral equality of a black-box LLM to a locally deployed authentic model. Our method is accurate, query-efficient, and avoids detectable query patterns, making it robust to adversarial providers that reroute or mix responses upon the detection of testing attempts. We evaluate the approach across diverse threat scenarios, including quantization, harmful fine-tuning, jailbreak prompts, and full model substitution, showing that it consistently achieves superior statistical power over prior methods under constrained query budgets.

Jiaming Ji, Kaile Wang, Tianyi Qiu et al.

Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment process can be easily circumvented, whether intentionally or accidentally. Does alignment fine-tuning yield have robust effects on models, or are its impacts merely superficial? In this work, we make the first exploration of this phenomenon from both theoretical and empirical perspectives. Empirically, we demonstrate the $\mathbf{elasticity}$ of post-alignment models, i.e., the tendency to revert to the behavior distribution formed during the pre-training phase upon further fine-tuning. Leveraging compression theory, we formally deduce that fine-tuning disproportionately undermines alignment relative to pre-training, potentially by orders of magnitude. We validate the presence of elasticity through experiments on models of varying types and scales. Specifically, we find that model performance declines rapidly before reverting to the pre-training distribution, after which the rate of decline drops significantly. Furthermore, we further reveal that elasticity positively correlates with the increased model size and the expansion of pre-training data. Our findings underscore the need to address the inherent elasticity of LLMs to mitigate their resistance to alignment. The model weight and code are available at pku-lm-resist-alignment.github.io.