Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards. Recent RLVR works that operate under the zero setting avoid supervision in labeling the reasoning process, but still depend on manually curated collections of questions and answers for training. The scarcity of high-quality, human-produced examples raises concerns about the long-term scalability of relying on human supervision, a challenge already evident in the domain of language model pretraining. Furthermore, in a hypothetical future where AI surpasses human intelligence, tasks provided by humans may offer limited learning potential for a superintelligent system. To address these concerns, we propose a new RLVR paradigm called Absolute Zero, in which a single model learns to propose tasks that maximize its own learning progress and improves reasoning by solving them, without relying on any external data. Under this paradigm, we introduce the Absolute Zero Reasoner (AZR), a system that self-evolves its training curriculum and reasoning ability by using a code executor to both validate proposed code reasoning tasks and verify answers, serving as an unified source of verifiable reward to guide open-ended yet grounded learning. Despite being trained entirely without external data, AZR achieves overall SOTA performance on coding and mathematical reasoning tasks, outperforming existing zero-setting models that rely on tens of thousands of in-domain human-curated examples. Furthermore, we demonstrate that AZR can be effectively applied across different model scales and is compatible with various model classes.

This study investigates whether individuals can learn to accurately discriminate between human-written and AI-produced texts when provided with immediate feedback, and if they can use this feedback to recalibrate their self-perceived competence. We also explore the specific criteria individuals rely upon when making these decisions, focusing on textual style and perceived readability. We used GPT-4o to generate several hundred texts across various genres and text types comparable to Koditex, a multi-register corpus of human-written texts. We then presented randomized text pairs to 254 Czech native speakers who identified which text was human-written and which was AI-generated. Participants were randomly assigned to two conditions: one receiving immediate feedback after each trial, the other receiving no feedback until experiment completion. We recorded accuracy in identification, confidence levels, response times, and judgments about text readability along with demographic data and participants' engagement with AI technologies prior to the experiment. Participants receiving immediate feedback showed significant improvement in accuracy and confidence calibration. Participants initially held incorrect assumptions about AI-generated text features, including expectations about stylistic rigidity and readability. Notably, without feedback, participants made the most errors precisely when feeling most confident -- an issue largely resolved among the feedback group. The ability to differentiate between human and AI-generated texts can be effectively learned through targeted training with explicit feedback, which helps correct misconceptions about AI stylistic features and readability, as well as potential other variables that were not explored, while facilitating more accurate self-assessment. This finding might be particularly important in educational contexts.

Lay summaries for scientific documents typically include explanations to help readers grasp sophisticated concepts or arguments. However, current automatic summarization methods do not explicitly model explanations, which makes it difficult to align the proportion of explanatory content with human-written summaries. In this paper, we present a plan-based approach that leverages discourse frameworks to organize summary generation and guide explanatory sentences by prompting responses to the plan. Specifically, we propose two discourse-driven planning strategies, where the plan is conditioned as part of the input or part of the output prefix, respectively. Empirical experiments on three lay summarization datasets show that our approach outperforms existing state-of-the-art methods in terms of summary quality, and it enhances model robustness, controllability, and mitigates hallucination.

While metrics available during pre-training, such as perplexity, correlate well with model performance at scaling-laws studies, their predictive capacities at a fixed model size remain unclear, hindering effective model selection and development. To address this gap, we formulate the task of selecting pre-training checkpoints to maximize downstream fine-tuning performance as a pairwise classification problem: predicting which of two LLMs, differing in their pre-training, will perform better after supervised fine-tuning (SFT). We construct a dataset using 50 1B parameter LLM variants with systematically varied pre-training configurations, e.g., objectives or data, and evaluate them on diverse downstream tasks after SFT. We first conduct a study and demonstrate that the conventional perplexity is a misleading indicator. As such, we introduce novel unsupervised and supervised proxy metrics derived from pre-training that successfully reduce the relative performance prediction error rate by over 50%. Despite the inherent complexity of this task, we demonstrate the practical utility of our proposed proxies in specific scenarios, paving the way for more efficient design of pre-training schemes optimized for various downstream tasks.

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in training data, linguistic imbalances, or adversarial manipulation. Despite mitigation efforts, recent studies show that LLMs remain vulnerable to adversarial attacks that elicit biased outputs. This work proposes a scalable benchmarking framework to assess LLM robustness to adversarial bias elicitation. Our methodology involves: (i) systematically probing models across multiple tasks targeting diverse sociocultural biases, (ii) quantifying robustness through safety scores using an LLM-as-a-Judge approach, and (iii) employing jailbreak techniques to reveal safety vulnerabilities. To facilitate systematic benchmarking, we release a curated dataset of bias-related prompts, named CLEAR-Bias. Our analysis, identifying DeepSeek V3 as the most reliable judge LLM, reveals that bias resilience is uneven, with age, disability, and intersectional biases among the most prominent. Some small models outperform larger ones in safety, suggesting that training and architecture may matter more than scale. However, no model is fully robust to adversarial elicitation, with jailbreak attacks using low-resource languages or refusal suppression proving effective across model families. We also find that successive LLM generations exhibit slight safety gains, while models fine-tuned for the medical domain tend to be less safe than their general-purpose counterparts.

Large Reasoning Models (LRMs) such as DeepSeek-R1 and OpenAI o1 have demonstrated remarkable capabilities in various reasoning tasks. Their strong capability to generate and reason over intermediate thoughts has also led to arguments that they may no longer require extensive prompt engineering or optimization to interpret human instructions and produce accurate outputs. In this work, we aim to systematically study this open question, using the structured task of event extraction for a case study. We experimented with two LRMs (DeepSeek-R1 and o1) and two general-purpose Large Language Models (LLMs) (GPT-4o and GPT-4.5), when they were used as task models or prompt optimizers. Our results show that on tasks as complicated as event extraction, LRMs as task models still benefit from prompt optimization, and that using LRMs as prompt optimizers yields more effective prompts. Our finding also generalizes to tasks beyond event extraction. Finally, we provide an error analysis of common errors made by LRMs and highlight the stability and consistency of LRMs in refining task instructions and event guidelines.

Model diffing is the study of how fine-tuning changes a model's representations and internal algorithms. Many behaviors of interest are introduced during fine-tuning, and model diffing offers a promising lens to interpret such behaviors. Crosscoders are a recent model diffing method that learns a shared dictionary of interpretable concepts represented as latent directions in both the base and fine-tuned models, allowing us to track how concepts shift or emerge during fine-tuning. Notably, prior work has observed concepts with no direction in the base model, and it was hypothesized that these model-specific latents were concepts introduced during fine-tuning. However, we identify two issues which stem from the crosscoders L1 training loss that can misattribute concepts as unique to the fine-tuned model, when they really exist in both models. We develop Latent Scaling to flag these issues by more accurately measuring each latent's presence across models. In experiments comparing Gemma 2 2B base and chat models, we observe that the standard crosscoder suffers heavily from these issues. Building on these insights, we train a crosscoder with BatchTopK loss and show that it substantially mitigates these issues, finding more genuinely chat-specific and highly interpretable concepts. We recommend practitioners adopt similar techniques. Using the BatchTopK crosscoder, we successfully identify a set of chat-specific latents that are both interpretable and causally effective, representing concepts such as $\textit{false information}$ and $\textit{personal question}$, along with multiple refusal-related latents that show nuanced preferences for different refusal triggers. Overall, our work advances best practices for the crosscoder-based methodology for model diffing and demonstrates that it can provide concrete insights into how chat-tuning modifies model behavior.

MOVEMETHOD is a hallmark refactoring. Despite a plethora of research tools that recommend which methods to move and where, these recommendations do not align with how expert developers perform MOVEMETHOD. Given the extensive training of Large Language Models and their reliance upon naturalness of code, they should expertly recommend which methods are misplaced in a given class and which classes are better hosts. Our formative study of 2016 LLM recommendations revealed that LLMs give expert suggestions, yet they are unreliable: up to 80% of the suggestions are hallucinations. We introduce the first LLM fully powered assistant for MOVEMETHOD refactoring that automates its whole end-to-end lifecycle, from recommendation to execution. We designed novel solutions that automatically filter LLM hallucinations using static analysis from IDEs and a novel workflow that requires LLMs to be self-consistent, critique, and rank refactoring suggestions. As MOVEMETHOD refactoring requires global, projectlevel reasoning, we solved the limited context size of LLMs by employing refactoring-aware retrieval augment generation (RAG). Our approach, MM-assist, synergistically combines the strengths of the LLM, IDE, static analysis, and semantic relevance. In our thorough, multi-methodology empirical evaluation, we compare MM-assist with the previous state-of-the-art approaches. MM-assist significantly outperforms them: (i) on a benchmark widely used by other researchers, our Recall@1 and Recall@3 show a 1.7x improvement; (ii) on a corpus of 210 recent refactorings from Open-source software, our Recall rates improve by at least 2.4x. Lastly, we conducted a user study with 30 experienced participants who used MM-assist to refactor their own code for one week. They rated 82.8% of MM-assist recommendations positively. This shows that MM-assist is both effective and useful.

The edifice of native Vision-Language Models (VLMs) has emerged as a rising contender to typical modular VLMs, shaped by evolving model architectures and training paradigms. Yet, two lingering clouds cast shadows over its widespread exploration and promotion: (-) What fundamental constraints set native VLMs apart from modular ones, and to what extent can these barriers be overcome? (-) How to make research in native VLMs more accessible and democratized, thereby accelerating progress in the field. In this paper, we clarify these challenges and outline guiding principles for constructing native VLMs. Specifically, one native VLM primitive should: (i) effectively align pixel and word representations within a shared semantic space; (ii) seamlessly integrate the strengths of formerly separate vision and language modules; (iii) inherently embody various cross-modal properties that support unified vision-language encoding, aligning, and reasoning. Hence, we launch NEO, a novel family of native VLMs built from first principles, capable of rivaling top-tier modular counterparts across diverse real-world scenarios. With only 390M image-text examples, NEO efficiently develops visual perception from scratch while mitigating vision-language conflicts inside a dense and monolithic model crafted from our elaborate primitives. We position NEO as a cornerstone for scalable and powerful native VLMs, paired with a rich set of reusable components that foster a cost-effective and extensible ecosystem. Our code and models are publicly available at: https://github.com/EvolvingLMMs-Lab/NEO.

Recent image editing models have achieved impressive results while following natural language editing instructions, but they rely on supervised fine-tuning with large datasets of input-target pairs. This is a critical bottleneck, as such naturally occurring pairs are hard to curate at scale. Current workarounds use synthetic training pairs that leverage the zero-shot capabilities of existing models. However, this can propagate and magnify the artifacts of the pretrained model into the final trained model. In this work, we present a new training paradigm that eliminates the need for paired data entirely. Our approach directly optimizes a few-step diffusion model by unrolling it during training and leveraging feedback from vision-language models (VLMs). For each input and editing instruction, the VLM evaluates if an edit follows the instruction and preserves unchanged content, providing direct gradients for end-to-end optimization. To ensure visual fidelity, we incorporate distribution matching loss (DMD), which constrains generated images to remain within the image manifold learned by pretrained models. We evaluate our method on standard benchmarks and include an extensive ablation study. Without any paired data, our method performs on par with various image editing diffusion models trained on extensive supervised paired data, under the few-step setting. Given the same VLM as the reward model, we also outperform RL-based techniques like Flow-GRPO.