Better with Experience: Self-Evolving LLM Agents for Evidence-Grounded Health Community Notes

Large Language Model (LLM)-augmented Community Notes offer a scalable path for timely, evidence-grounded correction of health misinformation on social platforms. However, they still reset at every post, leaving useful correction experience from prior cases unused. We introduce EvoNote, an agentic framework that enables health Community Notes generation to self-evolve through an evolving experience memory of prior misinformation correction episodes. Its core is fine-grained credit assignment: EvoNote grounds trajectory-level feedback in health-specific note qualities and distills it into action-level memory for claim analysis, evidence acquisition, and note writing. We evaluate EvoNote on MM-HealthCN, a 1.2K-instance multimodal benchmark of user-flagged health posts with human-written Community Notes and crowd-derived helpfulness labels. Under a human-validated hierarchical utility judge, EvoNote-generated notes are preferred over corresponding human-written notes in 89.6% of cases; on a separate set of Needs More Ratings posts without a crowd helpfulness verdict, EvoNote produces helpful notes for 82.0% of cases. It also reduces the median time needed to produce a candidate correction from over 13 hours in the human-note pipeline to under 2 minutes. Analyses link these gains to stronger evidence use and reusable correction strategies, positioning self-evolving note generation as a promising paradigm for health misinformation governance.

Uncovering Temporal Framing in the News

Temporal language does more than place events on a timeline. In news discourse, references to the past, present, and future can function as rhetorical devices that shape interpretation and persuasion. Here, we study temporal framing, defined as the persuasive use of time-related language to structure meaning rather than to report chronology. We propose a taxonomy of eight temporal frames grounded in prior work on temporality and framing, and we realize it through expert annotation of a multilingual news corpus. The resulting dataset includes 458 English and German news articles, with over 2K temporally framed sentences and approximately 3K temporal framing annotations identified from a corpus of more than 20K sentences. We analyze frame prevalence, co-occurrence patterns, and lexical cues, and evaluate temporal framing detection using supervised fine-tuning and zero-shot classification. Our experiments show that temporal framing is learnable at the sentence level, with supervised models substantially outperforming zero-shot approaches. We publicly release the corpus to support future research on temporal framing: https://mbzuai-nlp.github.io/temporal-framing/.

The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations

Large language models confidently produce outdated answers, and no existing method can detect them. We show this is not an engineering failure but a structural one: temporal drift, whether a stored fact has changed since training, is encoded as a direction in the residual stream geometrically orthogonal to both correctness and uncertainty. Any method operating on correctness or uncertainty signals is therefore blind to drift by construction. We verify this across six instruction-tuned models. A linear probe trained directly on drift labels achieves AUROC $0.83$--$0.95$; methods based on token entropy, semantic entropy, CCS, and SAPLMA all remain near chance ($0.49$--$0.57$). Five tests confirm the geometric orthogonality: weight cosines ($|\cos| \leq 0.14$), score correlations ($|r| \leq 0.20$), bidirectional null-space projection ($|Δ| \leq 0.008$), iterative null-space projection with $k{=}10$, and difference-of-means dissociation. Mechanistically, the MLP retrieval circuit produces identical dynamics for stale recall and confabulation ($r > 0.81$, six models), explaining why output confidence cannot separate them. A cross-cutoff experiment holds inputs constant and varies only the model: the probe fires on the model whose training predates the fact's transition and stays silent otherwise ($P(A{>}B) = 0.975$--$0.998$, twelve model pairs), confirming it reads model-internal knowledge state rather than input properties. Our code and datasets will be publicly released.

FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals

SemEval-2026 Task 13 investigates machine-generated code detection across multiple programming languages and application scenarios, asking participating systems to generalize to unseen languages and domains. This paper describes our participation in Subtask A (binary classification) and explores both pretrained code encoders and lightweight feature-based methods. We design ratio-based features that are less sensitive to snippet length. To support the extraction of descriptiveness-related signals, we use parsing engines and a programming-language classifier. Additionally, we train a separate code-vs-text line classifier to identify raw natural language segments embedded within samples. We combine a shallow decision tree with heuristic rules derived from data analysis to produce the final predictions. Our approach is computationally efficient, requires only CPU resources for training, and achieves near-instant inference time, offering a lightweight alternative to large pretrained models.

The Cylindrical Representation Hypothesis for Language Model Steering

Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical accounts are largely based on the Linear Representation Hypothesis (LRH). While LRH assumes that concepts can be orthogonalized for lossless control, this idealized mapping fails in real representations and cannot account for the observed unpredictability of steering. By relaxing LRH's orthogonality assumption while preserving linear representations, we show that overlapping concept contributions naturally yield a sample-specific axis-orthogonal structure. We formalize this as the Cylindrical Representation Hypothesis (CRH). In CRH, a central axis captures the main difference between concept absence and presence and drives concept generation. A surrounding normal plane controls steering sensitivity by determining how easily the axis can activate the target concept. Within this plane, only specific sensitive sectors strongly facilitate concept activation, while other sectors can suppress or delay it. While the surrounding normal plane can be reliably identified from difference vectors, the sensitive sector cannot, introducing intrinsic uncertainty at the sector level. This uncertainty provides a principled explanation for why steering outcomes often fluctuate even when using well-aligned directions. Our experiments verify the existence of the cylindrical structure and demonstrate that CRH provides a valid and practical way to interpret model steering behavior in real settings: https://github.com/mbzuai-nlp/CRH.

SAHM: A Benchmark for Arabic Financial and Shari'ah-Compliant Reasoning

English financial NLP has progressed rapidly through benchmarks for sentiment, document understanding, and financial question answering, while Arabic financial NLP remains comparatively under-explored despite strong practical demand for trustworthy finance and Islamic-finance assistants. We introduce SAHM, a document-grounded benchmark and instruction-tuning dataset for Arabic financial NLP and Shari'ah-compliant reasoning. SAHM contains 14,380 expert-verified instances spanning seven tasks: AAOIFI standards QA, fatwa-based QA/MCQ, accounting and business exams, financial sentiment analysis, extractive summarization, and event-cause reasoning, curated from authentic regulatory, juristic, and corporate sources. We evaluate 19 strong open and proprietary LLMs using task-specific metrics and rubric-based scoring for open-ended outputs, and find that Arabic fluency does not reliably translate to evidence-grounded financial reasoning: models are substantially stronger on recognition-style tasks than on generation and causal reasoning, with the largest gaps on event-cause reasoning. We release the benchmark, evaluation framework, and an instruction-tuned model to support future research on trustworthy Arabic financial NLP.

Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models

Large language models (LLMs) are prone to generating factually incorrect outputs. Recent work has applied conformal prediction to provide uncertainty estimates and statistical guarantees for the factuality of LLM generations. However, existing approaches are typically not prompt-adaptive, limiting their ability to capture input-dependent variability. As a result, they may filter out too few items (leading to over-coverage) or too many (under-coverage) for a given task or prompt. We propose an adaptive conformal prediction approach that extends conformal score transformation methods to LLMs, with applications to long-form generation and multiple-choice question answering. This enables prompt-dependent calibration, retaining marginal coverage guarantees while improving conditional coverage. In addition, the approach naturally supports selective prediction, allowing unreliable claims or answer choices to be filtered out in downstream applications. We evaluate our approach on multiple white-box models across diverse domains and show that it significantly outperforms existing baselines in terms of conditional coverage.

Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models

Professional fact-checkers rely on domain knowledge and deep contextual understanding to verify claims. Large language models (LLMs) and large reasoning models (LRMs) lack such grounding and primarily reason from available evidence alone, creating a mismatch between expert-led and fully automated claim verification. To mitigate this gap, we posit human-AI collaboration as a more promising path forward, where expert feedback, grounded in real-world knowledge and domain expertise, guides the model's reasoning. However, existing LRMs are hard to calibrate to natural language feedback, particularly in a multi-turn interaction setup. We propose Co-FactChecker, a framework for human-AI collaborative claim verification. We introduce a new interaction paradigm that treats the model's thinking trace as a shared scratchpad. Co-FactChecker translates expert feedback into trace-edits that introduce targeted modifications to the trace, sidestepping the shortcomings of dialogue-based interaction. We provide theoretical results showing that trace-editing offers advantages over multi-turn dialogue, and our automatic evaluations demonstrate that Co-FactChecker outperforms existing autonomous and human-AI collaboration approaches. Human evaluations further show that Co-FactChecker is preferred over multi-turn dialogue, producing higher quality reasoning and verdicts along with relatively easier to interpret and more useful thinking traces.

Why Don't You Know? Evaluating the Impact of Uncertainty Sources on Uncertainty Quantification in LLMs

As Large Language Models (LLMs) are increasingly deployed in real-world applications, reliable uncertainty quantification (UQ) becomes critical for safe and effective use. Most existing UQ approaches for language models aim to produce a single confidence score -- for example, estimating the probability that a model's answer is correct. However, uncertainty in natural language tasks arises from multiple distinct sources, including model knowledge gaps, output variability, and input ambiguity, which have different implications for system behavior and user interaction. In this work, we study how the source of uncertainty impacts the behavior and effectiveness of existing UQ methods. To enable controlled analysis, we introduce a new dataset that explicitly categorizes uncertainty sources, allowing systematic evaluation of UQ performance under each condition. Our experiments reveal that while many UQ methods perform well when uncertainty stems solely from model knowledge limitations, their performance degrades or becomes misleading when other sources are introduced. These findings highlight the need for uncertainty-aware methods that explicitly account for the source of uncertainty in large language models.

ReDAct: Uncertainty-Aware Deferral for LLM Agents

Recently, LLM-based agents have become increasingly popular across many applications, including complex sequential decision-making problems. However, they inherit the tendency of LLMs to hallucinate, leading to incorrect decisions. In sequential settings, even a single mistake can irreversibly degrade the trajectory, making hallucinations an even bigger problem. Although larger LLMs hallucinate less, they incur a significantly higher per-token cost. In this paper, we address this tradeoff by proposing ReDAct (Reason-Defer-Act). In ReDAct, an agent is equipped with two LLMs: a small, cheap model used by default, and a large, more reliable but expensive model. When the predictive uncertainty of the small model exceeds a calibrated threshold, the decision is deferred to the large model. We evaluate our approach in text-based embodied environments such as ALFWorld and MiniGrid and show that deferring only about 15% of decisions to the large model can match the quality of using it exclusively, while significantly reducing inference costs.