Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale

• URL: http://arxiv.org/abs/2601.18730v1
• Date: Mon, 26 Jan 2026 17:54:54 GMT
• Title: Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale
• Authors: Henry Bell, Caroline Zhang, Mohammed Mobasserul Haque, Dhaval Potdar, Samia Zaman, Brandon Fain,
• Abstract summary: textscreflect is an inference-time framework for constitutional alignment.<n>textscreflect operates entirely in-context, combining a (i) constitution-conditioned base response with post-generation self-evaluation.<n>Our results demonstrate that textscreflect significantly improves LLM conformance to diverse and complex principles.
• Score: 0.225739374955489
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The constitutional framework of alignment aims to align large language models (LLMs) with value-laden principles written in natural language (such as to avoid using biased language). Prior work has focused on parameter fine-tuning techniques, such as reinforcement learning from human feedback (RLHF), to instill these principles. However, these approaches are computationally demanding, require careful engineering and tuning, and often require difficult-to-obtain human annotation data. We propose \textsc{reflect}, an inference-time framework for constitutional alignment that does not require any training or data, providing a plug-and-play approach for aligning an instruction-tuned model to a set of principles. \textsc{reflect} operates entirely in-context, combining a (i) constitution-conditioned base response with post-generation (ii) self-evaluation, (iii)(a) self-critique, and (iii)(b) final revision. \textsc{reflect}'s technique of explicit in-context reasoning over principles during post-generation outperforms standard few-shot prompting and provides transparent reasoning traces. Our results demonstrate that \textsc{reflect} significantly improves LLM conformance to diverse and complex principles, including principles quite distinct from those emphasized in the model's original parameter fine-tuning, without sacrificing factual reasoning. \textsc{reflect} is particularly effective at reducing the rate of rare but significant violations of principles, thereby improving safety and robustness in the tail end of the distribution of generations. Finally, we show that \textsc{reflect} naturally generates useful training data for traditional parameter fine-tuning techniques, allowing for efficient scaling and the reduction of inference-time computational overhead in long-term deployment scenarios.

Related papers

• Native Reasoning Models: Training Language Models to Reason on Unverifiable Data [16.065264121785294]
  We introduce NRT (Native Reasoning Training), a novel framework that cultivates complex reasoning.<n>NRT reframes the training problem by treating the reasoning process as a latent variable.<n>NRT achieves state-of-the-art performance among verifier-free methods.
  arXiv  Detail & Related papers  (2026-02-12T04:15:46Z)
• LLMs as High-Dimensional Nonlinear Autoregressive Models with Attention: Training, Alignment and Inference [15.493230983626281]
  Large language models (LLMs) based on transformer architectures are typically described through collections of architectural components and training procedures.<n>We formulate LLMs as high-dimensional nonlinear autoregressive models with attention-based dependencies.
  arXiv  Detail & Related papers  (2026-01-31T00:37:53Z)
• VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision [9.028503801131933]
  We introduce textbfVariance-textbfControlled textbfOptimization-based textbfREweighting (VCORE)<n>By adopting an optimization-theoretic perspective, VCORE enables a principled and adaptive allocation of supervision across tokens.<n> Empirical evaluations demonstrate that VCORE consistently outperforms existing token reweighting methods.
  arXiv  Detail & Related papers  (2025-10-31T13:19:24Z)
• Step-Aware Policy Optimization for Reasoning in Diffusion Large Language Models [57.42778606399764]
  Diffusion language models (dLLMs) offer a promising, non-autoregressive paradigm for text generation.<n>Current reinforcement learning approaches often rely on sparse, outcome-based rewards.<n>We argue that this stems from a fundamental mismatch with the natural structure of reasoning.
  arXiv  Detail & Related papers  (2025-10-02T00:34:15Z)
• Large Reasoning Models Learn Better Alignment from Flawed Thinking [56.08883934423522]
  Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer.<n>We propose RECAP, a principled reinforcement learning (RL) method for post-training that explicitly teaches models to override flawed reasoning trajectories.
  arXiv  Detail & Related papers  (2025-10-01T14:15:43Z)
• READER: Retrieval-Assisted Drafter for Efficient LLM Inference [0.0386965802948046]
  Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on latency inference.<n>This bottleneck has emerged as a central obstacle to the scalable deployment of large-scale generative models.<n>We present READER, a speculative decoding framework that bypasses the training of the auxiliary draft model.
  arXiv  Detail & Related papers  (2025-08-12T16:47:48Z)
• Deep Equilibrium models for Poisson Imaging Inverse problems via Mirror Descent [7.248102801711294]
  Deep Equilibrium Models (DEQs) are implicit neural networks with fixed points.<n>We introduce a novel DEQ formulation based on Mirror Descent defined in terms of a tailored non-Euclidean geometry.<n>We propose computational strategies that enable both efficient training and fully parameter-free inference.
  arXiv  Detail & Related papers  (2025-07-15T16:33:01Z)
• Reinforced Latent Reasoning for LLM-based Recommendation [92.56166822197919]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities in complex problem-solving tasks.<n>Existing methods typically rely on fine-tuning with explicit chain-of-thought (CoT) data.<n>In this work, we explore an alternative approach that shifts from explicit CoT reasoning to compact, information-dense latent reasoning.
  arXiv  Detail & Related papers  (2025-05-25T11:03:45Z)
• Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation [5.296260279593993]
  Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks.<n>We propose an optimal transport (OT)-guided prompt learning framework that mitigates forgetting by preserving the structural consistency of feature distributions.<n>Our approach enforces joint constraints on both vision and text representations, ensuring a holistic feature alignment.
  arXiv  Detail & Related papers  (2025-03-11T21:38:34Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• Decoding Human Preferences in Alignment: An Improved Approach to Inverse Constitutional AI [0.0]
  We develop a rule-based framework for aligning Large Language Models (LLMs)<n>We refine the Inverse Constitutional AI (ICAI) algorithm, which extracts constitutions from preference datasets.<n>Our results highlight the potential of these principles to foster more transparent and adaptable alignment methods.
  arXiv  Detail & Related papers  (2025-01-28T17:59:56Z)
• Deliberative Alignment: Reasoning Enables Safer Language Models [64.60765108418062]
  We introduce Deliberative Alignment, a new paradigm that teaches the model safety specifications and trains it to explicitly recall and accurately reason over the specifications before answering.<n>We used this approach to align OpenAI's o-series models, and achieved highly precise adherence to OpenAI's safety policies, without requiring human-written chain-of-thoughts or answers.
  arXiv  Detail & Related papers  (2024-12-20T21:00:11Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning [63.148199057487226]
  We propose a modular, NEuroSymbolic Textual Agent (NESTA) that combines a generic semantic generalization with a rule induction system to learn interpretable rules as policies. Our experiments show that the proposed NESTA method outperforms deep reinforcement learning-based techniques by achieving better to unseen test games and learning from fewer training interactions.
  arXiv  Detail & Related papers  (2023-07-05T23:21:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.