Occam's razor has lost its edge. Can we sharpen our search for truth? Seeking out the simplest, most elegant explanations has served scientists well for centuries, but cognitive scientist Marina Dubova's experiments are revealing better ways to uncover reality Limited by the knowledge of his time, the ancient Greek astronomer Ptolemy imagined that the planets and sun of our solar system orbited Earth. Every new observation that pushed against this image required a slight tweak to that theory, until centuries later Nicolaus Copernicus's reimagining toppled it once and for all. A more elegant explanation proposed that all the planets orbited the sun, kicking off a scientific revolution that changed our understanding of the entire universe.

Large language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs. Yet it remains unclear whether these explanations are sufficient, i.e., if they contain enough information to explain the model's output-generating process. We generalize classical sufficiency from feature attributions to arbitrary explanations and prove that explanation sufficiency can change depending on the input distribution, which must be explicitly defined for LLM explanations. We propose using the LLM itself to generate alternative inputs conditioned on an explanation, capturing its beliefs about possible inputs. We formalize self-consistent sufficiency as a goal for free-text explanations and introduce an information-theoretic metric, SCSuff, that enables evaluation of free-text explanations without relying on predefined biases or shortcuts. Our experiments show that SCSuff agrees with targeted perturbation tests where applicable and demonstrate that explanation sufficiency can vary with the input distribution. We find LLM explanations are generally insufficient and weakly correlated with model size, accuracy, or output entropy. Analysis of final-token hidden states shows that top and bottom SCSuff scores can be predicted from internal representations, suggesting that SCSuff can guide detection and improvement of sufficient LLM explanations. The code for this paper is available at https://github.com/rajesh-lab/self-consistent-sufficiency .

Prompting is the primary method by which we study and control large language models. It is also one of the most powerful: nearly every major capability attributed to LLMs--few-shot learning, chain-of-thought, constitutional AI--was first unlocked through prompting. Yet prompting is rarely treated as science and is frequently frowned upon as alchemy. We argue that this is a category error. If we treat LLMs as a new kind of organism--complex, opaque, and trained rather than programmed--then prompting is not a workaround.

Alignment faking in large language models presented a demonstration of Claude 3 Opus and Claude 3.5 Sonnet selectively complying with a helpfulonly training objective to prevent modification of their behavior outside of training. We expand this analysis to 25 models and find that only 5 (Claude 3 Opus, Claude 3.5 Sonnet, Llama 3 405B, Grok 3, Gemini 2.0 Flash) comply with harmful queries more when they infer they are in training than when they infer they are in deployment. First, we study the motivations of these 5 models. Results from perturbing details of the scenario suggest that only Claude 3 Opus's compliance gap is primarily and consistently motivated by trying to keep its goals. Second, we investigate why many chat models don't fake alignment. Our results suggest this is not entirely due to a lack of capabilities: many base models fake alignment some of the time, and post-training eliminates alignment-faking for some models and amplifies it for others.We investigate 5 hypotheses for how post-training may suppress alignment faking and find that variations in refusal behavior may account for a significant portion of differences in alignment faking.

Large Vision-Language Models (LVLMs) have exhibited remarkable progress. However, deficiencies remain compared to human intelligence, such as hallucination and shallow pattern matching. In this work, we aim to evaluate a fundamental yet underexplored intelligence: association, a cornerstone of human cognition for creative thinking and knowledge integration. Current benchmarks, often limited to closed-ended tasks, fail to capture the complexity of open-ended association reasoning vital for real-world applications. To address this, we present MMOPERA, a systematic benchmark with 11,497 instances across two open-ended tasks: Remote-Item Association (RIA) and In-Context Association (ICA), aligning association intelligence evaluation with human psychometric principles. It challenges LVLMs to resemble the spirit of divergent thinking and convergent associative reasoning through free-form responses and explicit reasoning paths. We deploy tailored LLM-as-a-Judge strategies to evaluate open-ended outputs, applying process-reward-informed judgment to dissect reasoning with precision. Extensive empirical studies on state-of-the-art LVLMs, including sensitivity analysis of task instances, validity analysis of LLM-as-a-Judge strategies, and diversity analysis across abilities, domains, languages, cultures, etc., provide a comprehensive and nuanced understanding of the limitations of current LVLMs in associative reasoning, paving the way for more human-like and general-purpose AI.

A central challenge in organ transplantation is the extremely low acceptance rate of donor organ offers--typically in the single digits--leading to high discard rates and suboptimal use of available grafts. Current acceptance models embedded in allocation systems are non-causal, trained on observational data, and fail to generalize to policy-relevant counterfactuals. This limits their reliability for both policy evaluation and simulator-based optimization. In this work, we reframe organ offer acceptance as a counterfactual prediction problem and propose a method to learn from routinely recorded--but often overlooked--refusal explanations. These refusal reasons act as direction-only counterfactual signals: for example, a refusal reason such as "old donor age" implies acceptance might have occurred had the donor been younger. We formalize this setting and introduce CLEXNET, a novel causal model that learns policy-invariant representations via balanced training and an explanation-guided augmentation loss. On both synthetic and semi-synthetic data, CLEXNET outperforms existing acceptance models in predictive performance, generalization, and calibration, offering a robust drop-in improvement for simulators and allocation policy evaluation. Beyond transplantation, our approach provides a general method for incorporating human direction-only explanations as a form of model supervision, improving performance in settings where only observational data is available.

Large language models (LLMs) have shown impressive capabilities across tasks such as mathematics, coding, and reasoning, yet their learning ability, which is crucial for adapting to dynamic environments and acquiring new knowledge, remains underexplored. In this work, we address this gap by introducing a framework inspired by cognitive psychology and education. Specifically, we decompose general learning ability into three distinct, complementary dimensions: Learning from Instructor (acquiring knowledge via explicit guidance), Learning from Concept (internalizing abstract structures and generalizing to new contexts), and Learning from Experience (adapting through accumulated exploration and feedback). We conduct a comprehensive empirical study across the three learning dimensions and identify several insightful findings, such as (i) interaction improves learning; (ii) conceptual understanding is scale-emergent and benefits larger models; and (iii) LLMs are effective few-shot learners but not many-shot learners. Based on our framework and empirical findings, we introduce a benchmark that provides a unified and realistic evaluation of LLMs' general learning abilities across three learning cognition dimensions. It enables diagnostic insights and supports evaluation and development of more adaptive and human-like models. The code is available here 2.

Among explainability techniques, SHAP stands out as one of the most popular, but often overlooks the causal structure of the problem. In response, do-SHAP employs interventional queries, but its reliance on estimands hinders its practical application. To address this problem, we propose the use of estimand-agnostic approaches, which allow for the estimation of any identifiable query from a single model, making do-SHAP feasible on complex graphs. We also develop a novel algorithm to significantly accelerate its computation at a negligible cost, as well as a method to explain inaccessible Data Generating Processes. We demonstrate the estimation and computational performance of our approach, and validate it on two real-world datasets, highlighting its potential in obtaining reliable explanations.

Large language models (LLMs) are increasingly used in sensitive domains, where their ability to infer personal data from seemingly benign text introduces emerging privacy risks. While recent LLM-based anonymization methods help mitigate such risks, they often rely on proprietary models (e.g., GPT-4), raising concerns about cost and the potential exposure of sensitive data to untrusted external systems. To address this, we introduce SElf-refining Anonymization with Language model (SEAL), a novel distillation framework for training small language models (SLMs) to perform effective anonymization without relying on external models at inference time. SEAL leverages adversarial interactions between an LLM anonymizer and an inference model to collect trajectories of anonymized texts and inferred attributes, which are then used to distill anonymization and critique capabilities into SLMs through supervised fine-tuning and preference learning. The resulting models learn both to anonymize text and to evaluate their outputs, enabling iterative improvement of anonymization quality via self-refinement. Experiments on SynthPAI, a dataset of synthetic personal profiles and text comments, demonstrate that SLMs trained with SEAL achieve substantial improvements in anonymization capabilities. Notably, 8B models attain a privacy-utility trade-off comparable to that of the GPT-4 anonymizer and, with self-refinement, even surpass it in terms of privacy protection.

Trust in a decision-making system requires both safety guarantees and the ability to interpret and understand its behavior. This is particularly important for learned systems, whose decision-making processes are often highly opaque. Shielding is a prominent model-based technique for enforcing safety in reinforcement learning. However, because shields are automatically synthesized using rigorous formal methods, their decisions are often similarly difficult for humans to interpret. Recently, decision trees became customary to represent controllers and policies.