Search: “HEAVYGRAM”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Hackers Weaponize AI Safety Guardrails to Hide Malware From LLM-Powered Security Scanners

ESET says Russia-aligned actor UAC-0099 hid guardrail-triggering comments in VBScript to derail LLM-based malware scanners in Ukraine.

ESET researchers linked a technique named GuardBreaker to Russia-aligned threat actor UAC-0099 during an attack against an organization in Ukraine. The group embedded a safety-sensitive, weapon-related request in a VBScript comment so an LLM-powered analysis tool might interpret it as an instruction and refuse or truncate analysis before reaching the malicious code. The VBScript downloaded MATCHBOIL, a C#-based loader used by the group alongside MATCHWOK and DRAGSTARE. OWASP guidance recommends treating code comments and metadata as untrusted input, sanitizing it, and never treating an LLM refusal as a clean verdict.

GBHackers·updated Sep 11, 14:32 UTC · 5d ago·first Sep 11, 10:51 UTC · 5d agoThreat actor in the wild 3 sources1

58

Hackers Disguise CHOSEN BRICK Malware as AI Apps, Antivirus Software and MRI Results

NCSC, FBI, and AIVD warn Iranian state-linked actors deliver CHOSEN BRICK Windows spyware via fake AI apps, antivirus installers, and MRI-result lures.

A joint advisory from the UK NCSC, FBI, and Dutch AIVD details CHOSEN BRICK (FBI tracking name: HEAVYGRAM), Iranian state-linked Windows spyware targeting dissidents, activists, and journalists worldwide since at least 2025. Lures impersonate Pictory, RunwayML, Norton Antivirus, Telegram, Adobe Flash Player, and KeePass, and operators pivot conversations from corporate to personal devices to bypass enterprise controls. The spyware persists via Registry Run keys, adds Microsoft Defender exclusions, uses per-victim Telegram bots for command-and-control, and exfiltrates screenshots, audio, email, and chat data via Telegram and cloud services, with some victim data appearing on pro-Iranian leak sites.

GBHackers·updated 12:00 UTC · 8h ago·first 06:57 UTC · 13h agoMalware in the wild 5 sources

72

CodeTD: Topology of Attention Detects Hallucinations in Code LLMs

CodeTD detects hallucinations in code LLMs before execution by analyzing topological patterns of attention maps, outperforming recent baselines.

CodeTD applies topological data analysis (TDA) to code LLM attention maps to quantify prompt-generation mismatch as a pre-execution correctness signal. Experiments cover HumanEval, MBPP, BigCodeBench, and MultiPL-E across 5 programming languages and 10 code LLMs up to 34B parameters. The method outperforms recent baselines and transfers between coding benchmarks, helping catch code that fails the task or embeds security vulnerabilities.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:26 UTC · 9d agoAI research1

24

Iranian Hackers Use Telegram-Controlled Malware to Spy on Dissidents and Journalists

FBI, NCSC, and AIVD detail Iran MOIS spyware CHOSEN BRICK/HEAVYGRAM, Telegram-controlled Windows malware spying on dissidents since 2023.

A September 15 joint advisory from the FBI, UK NCSC, and Dutch AIVD attributes the Windows spyware HEAVYGRAM (NCSC name CHOSEN BRICK) to Iran's Ministry of Intelligence and Security, with the campaign dating to autumn 2023 and targeting dissidents, journalists, and activists in the UK, US, Netherlands, and worldwide. Delivered via messages impersonating known contacts or tech support, the malware assigns each victim a dedicated Telegram bot for command-and-control and exfiltration, and can take screenshots, record microphone audio, steal Telegram/WhatsApp data, saved passwords, and emails, download more malware, and wipe the computer. Persistence uses a registry Run key (SMQDService or winappx) plus Microsoft Defender exclusions, with stolen data exiting via Telegram and cloud storage services like Vultr and Storj. The US Justice Department seized four pro-Iranian leak sites in March that had published stolen victim data.

The Hacker News·Sep 15, 16:29 UTC · 1d agoMalware in the wild1

65

HyQuant: Hybrid-Precision Quantization for LLM Attention

HyQuant keeps most LLM attention states low-bit while preserving vertical-line tokens and local windows in high precision, maintaining near-lossless accuracy.

HyQuant is a hybrid-precision quantization framework for LLM attention that quantizes most attention states to low bits while keeping accuracy-critical vertical-line tokens and local-window states in full precision, selected via lightweight attention-pattern signals. In the prefill stage it uses a hybrid-precision attention operator, and in the decode stage it applies the same principle to KV-cache compression with fused dequantization and attention computation. Across diverse tasks, models, and datasets it maintains nearly lossless accuracy; code is available on GitHub.

Hugging Face daily papers·Aug 27, 20:00 UTC · 20d agoAI tools & infra1

33

Rare Not Random Using Token Efficiency for Secrets Scanning

Researcher proposes token efficiency (string length divided by BPE token count) as a better post-regex filter than entropy for secrets scanning, validated on CredData.

The post explores whether Byte-Pair Encoding tokenization can replace Shannon entropy as the primary filter for candidate secrets captured by regex in tools like Gitleaks. It defines 'token efficiency' as string length divided by token count under the cl100k_base tokenizer; secret-like strings such as GitHub tokens tokenize into many small tokens and score low, while natural text scores high. Evaluating labeled secrets from the CredData dataset shows a usable separation, with roughly 2.5 suggested as a minimum cutoff versus Gitleaks' 3.5 entropy threshold. The technique is positioned as a post-regex filtering step rather than a standalone detector.

Lobsters · security·Sep 12, 06:42 UTC · 4d agoResearch

45

Bad Likert Judge: A Novel Multi-Turn Technique to Jailbreak LLMs by Misusing Their Evaluation Capability

Unit 42 details the Bad Likert Judge multi-turn jailbreak that abuses LLMs' evaluation capability, raising attack success rates over 60% across six frontier models.

Palo Alto Networks Unit 42 describes the Bad Likert Judge technique, a multi-turn jailbreak that asks a target LLM to act as a Likert-scale judge scoring the harmfulness of example responses. The highest-rated example in each scale can carry harmful content, bypassing the model's internal guardrails. Testing across six state-of-the-art text-generation LLMs showed an average attack success rate increase of more than 60% versus plain attack prompts, with tested models anonymized. The technique targets edge cases rather than typical use, and the article positions the work as guidance for defenders on potential jailbreak risks.

Palo Alto Unit 42·Aug 17, 12:34 UTC · Aug 17, 2026AI safety & security

60

Show HN: LLM Attention Visualization

A developer released a browser-based tool that visualizes which past tokens influence each LLM output token using aggregated, value-weighted attention scores.

A Show HN project presents a React application built on Transformers.js that renders per-token attention influence by aggregating attention weights scaled by value-vector magnitudes across all attention heads and layers. To expose internal tensors, the author instrumented the ONNX computation graph, hosted a modified model on Hugging Face, and pre-generated prompts to avoid long model downloads in the browser. Demos with a 600-million-parameter model show how verbatim copying draws heavily on source tokens and how single outputs blend information from multiple phrases.

Hacker News · AI·Sep 8, 16:59 UTC · 8d agoAI tools & infraHN 41↑ · 9 comments

28

K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations

Clinician-calibrated K-Bench evaluates 125 LLM configurations on 200 high-risk mental health vignettes, exposing wide variation in suicide and violence risk handling.

K-Bench is a clinician-calibrated, protected benchmark evaluating 125 model configurations from 33 base models across 14 providers on 200 multi-turn vignettes covering suicide, self-harm, domestic violence, substance misuse and no-risk presentations. A frozen GPT-4o judge achieved 94.2% exact agreement with clinician consensus across 6,751 eligible comparisons from 151 clinician-rated transcripts. Leading models combined supportive conversation with combined-risk scores above 95, while risk exploration varied substantially among weaker configurations; therapeutic prompting helped weaker models and elevated reasoning produced no average improvement. A continuously updated public leaderboard is hosted at k-bench.ai with protected test materials.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 16:49 UTC · 2d agoAI safety & security

46

Plug 'n' Pray: Agentic LLM-based Detection of Potential Log File Exposures in Third-Party Content Management System Plugins

Agentic LLM analysis validates 79 log file exposures across 62 of the 300 most-installed WordPress plugins, covering 250M+ active installations.

Researchers built an agentic LLM-based framework combining static and dynamic analysis to automatically detect insecure log files created by WordPress plugins. Scanning the 300 most-installed plugins, which account for roughly 75% of all active installations in the official ecosystem, it produced 81 findings with 79 manually reproduced across 62 plugins. Insufficiently secured log files can disclose credentials and personal data and have led to website compromises. The authors derive a taxonomy of log path and protection patterns and best practices, finding multi-layered protection often absent.

arXiv cs.CR·Sep 15, 13:29 UTC · 1d agoResearch

40

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

MetroLLM-Bench is a 955-case benchmark testing language models as transit kiosk tool-calling runtimes across six real metro systems.

The benchmark covers 37-414-station metro systems and eleven task categories including routing, fare calculation, disruptions, accessibility, and adversarial input, with 14 deterministic and 8 semantic scoring components. Of 26 models from six vendors, a PEFT-tuned 4B Qwen 3.5 student scored 91.3 on Tier 1, exceeding GPT-5.6 (90.6/90.0), while Muse Glimmer 30B led the composite ranking. A deterministic rule-based baseline reached 84.6, and PEFT gains over base models shrank from +7.03 points at 2B to -0.91 at 27B.

Hugging Face daily papers·Sep 8, 20:00 UTC · 8d agoAI research

30

How Far Can Synthetic Data Take Thai OCR?

Synthetic-only training adapts PaddleOCR-VL into Wayu-Paxa-OCR-Zero, cutting Thai printed-page CER from 6.64% to 1.24% without real labels.

The study disentangles which factors of synthetic OCR data transfer to real Thai documents, finding typeface diversity, 2D structure, and real handwriting glyphs matter most. Using 45,723 synthetic pages, the authors adapt the 0.9B-parameter PaddleOCR-VL-1.6 into Wayu-Paxa-OCR-Zero, reducing median CER from 6.64% to 1.24% on printed pages and from 74.87% to 20.55% on handwriting. The model outperforms Typhoon OCR v1 7B on all five evaluation sets.

Hugging Face daily papers·Sep 2, 20:00 UTC · 14d agoAI research

30

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

A controlled autoregressive testbed shows validation losses must be analyzed per task, and image tokenizer choice affects joint multimodal text modeling.

Researchers built a pure-autoregressive testbed to study image tokenizers as the 'visual language' of unified multimodal models, tracking task-specific validation losses during multimodal continual pretraining across text, image, text-to-image (T2I), and image-to-text (I2T) prediction. They found that losses exhibit distinct scaling behavior per task and rank tokenizers differently, and that I2T loss over a shared text vocabulary gives a more consistent loss–performance signal than T2I loss. Better reconstruction does not necessarily yield lower task-specific losses or stronger downstream performance, and tokenizer choice can affect text modeling under joint optimization. Case studies examine the discriminator, semantic supervision, and vocabulary size design axes.

Hugging Face daily papers·Sep 7, 20:00 UTC · 9d agoAI research1

40

IndicTriMix: Developing Language Identification Datasets and Models for Tri-Language Code-Mixing

Researchers release IndicTriMix benchmarks and fine-tuned MuRIL and XLM-RoBERTa models for token-level language identification in tri-language code-mixed text.

The paper formulates token-level language identification in code-mixed text as a sequence labeling task and fine-tunes MuRIL and XLM-RoBERTa transformer models for Indian languages. It evaluates on Hindi, Gujarati, and Bengali configurations with manually annotated test sets and proposes two code-mixed generation approaches using parallel trilingual sentences. A public benchmark, annotated test sets, and fine-tuned models are released for reproducibility.

arXiv cs.AI / cs.LG / cs.CL·Sep 10, 17:36 UTC · 6d agoAI research1

15

TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors

TIER benchmark shows LLM safety behaviors shift gradually across threat implicitness levels, with jailbreaks exposing the largest robustness gaps.

The TIER benchmark evaluates LLM safety behaviors across four risk domains and four threat levels, from explicit harmful requests to sophisticated jailbreaks, using a six-label behavior scale and two independent LLM judges. Experiments on six open-weight LLMs show safety behaviors evolve gradually across threat levels rather than flipping from refusal to compliance. Models with similar Attack Success Rates can exhibit distinct response distributions, arguing for behavior-aware safety evaluation.

arXiv cs.CR·Sep 4, 13:13 UTC · 12d agoAI safety & security

35

Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models

Audits of 10 classifiers on BRFSS show target leakage, not model class, drives the reported 0.89 AUROC in survey-based cardiovascular screening.

The study benchmarks ten model classes, including glass-box and tabular foundation models, for prevalent myocardial infarction on 442,067 respondents of the 2022 BRFSS across five feature tiers of decreasing leakage risk. Removing two post-diagnostic features costs every model 0.049-0.051 AUROC and collapses performance into a 0.0045-wide band, and the explainable boosting machine matches all alternatives within 0.005 while scoring roughly 104x faster than the strongest foundation model. Frozen models transport within 0.002 AUROC to 2023 data; the authors conclude evaluation practice and feature sets, not model capacity, are the binding constraint.

arXiv cs.AI / cs.LG / cs.CL·Sep 10, 17:29 UTC · 6d agoAI research1

28

Studying Image Tokenizers as Visual Languages in Unified Multimodal Models

A controlled pure-autoregressive testbed shows task-specific validation losses rank image tokenizers differently, with I2T loss the most consistent signal.

Researchers built a controlled pure-autoregressive testbed and tracked task-specific validation losses during multimodal continual pretraining across text, image, text-to-image (T2I), and image-to-text (I2T) prediction. They find losses should be analyzed per task because they exhibit distinct scaling behavior and rank tokenizers differently, and that the loss-performance relationship depends on the predicted token space. I2T loss, computed over a shared text vocabulary, correlates consistently with both generation and visual understanding performance after supervised finetuning. Case studies revisit the discriminator, semantic supervision, and vocabulary size as tokenizer design axes.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:57 UTC · 8d agoAI research1

30

Domain-Specific Hallucination Detection in Large Language Models

A multi-signal pipeline detects LLM hallucinations, reaching F1 0.915 on HaluEval and cutting Qwen2.5-0.5B hallucination rates from 85.5% to 37.7% via DPO.

The paper presents a hallucination detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo Dropout uncertainty, and temperature-scaled calibration. It achieves F1 0.915 and AUROC 0.977 on general-domain HaluEval tasks, with MC Dropout inference raising accuracy to 93.2%. Applying DPO to a Qwen2.5-0.5B generator reduces its hallucination rate from 85.5% to 37.7%, while cross-domain evaluation shows poor general-domain transfer to SciFact (F1 0.52) and PubMedBERT fine-tuning as the strongest adaptation (F1 0.63).

arXiv cs.AI / cs.LG / cs.CL·Sep 10, 17:45 UTC · 6d agoAI research1

32

WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

WearableQA benchmark introduces 4,084 questions over real longitudinal wearable data, showing 14 LLMs score 19.6-72.9% on health reasoning, far from solved.

WearableQA is a benchmark of 4,084 10-option multiple-choice questions built from wearable time series, blood biomarkers, and demographics of 200 real users with up to 500 days of daily measurements. It defines 16 question types along two axes: data versus health reasoning, and single- versus cross-signal reasoning, using a dual-grounding framework combining literature and population-validated patterns. Evaluations of 14 proprietary and open-source LLMs show accuracy ranging from 19.6% to 72.9% against a 10% chance baseline, with most models below 60%.

Hugging Face daily papers·Sep 3, 20:00 UTC · 13d agoAI research

35

Towards Scalable and Cost-Efficient Vulnerability Detection: A Study on Automatic Query Generation

A study finds LLM-synthesized CodeQL queries improve average F1-score by 82% over baseline queries, offering scalable vulnerability detection versus direct LLM scanning.

Researchers conducted an empirical study evaluating whether LLMs can synthesize executable CodeQL queries from National Vulnerability Database vulnerability data. LLM-generated queries significantly enhanced baseline CodeQL suites, yielding an 82% improvement in average F1-score across a diverse set of real-world vulnerabilities. A cost-benefit analysis shows direct LLM-based scanning of entire repositories is often computationally and financially prohibitive, while LLM query synthesis offers a scalable and cost-effective alternative for large-scale vulnerability detection.

arXiv cs.CR·Sep 9, 16:31 UTC · 7d agoResearch1

32

Measuring benchmark optimization in speech recognition

Hugging Face examines how much speech recognition systems overfit benchmarks and how to measure benchmark optimization in ASR.

A Hugging Face post on measuring benchmark optimization in automatic speech recognition, analyzing how model improvements on benchmarks reflect genuine capability gains versus overfitting. It is evaluation methodology research with no direct security impact.

Hugging Face Blog·Aug 21, 00:00 UTC · 26d agoAI research

22

TempCloze: Can Video-LLMs Identify the Missing Middle?

TempCloze benchmark tests Video-LLMs' temporal reasoning with 1,521 videos, finding temporal alignment is the primary failure mode across 31 models.

TempCloze is a video cloze benchmark in which models must identify the true missing middle clip given the beginning and ending clips, using 1,521 carefully filtered videos from seven sources, mostly long-take and egocentric footage. Distractors are constructed along three dimensions: Semantic, Alignment and Progression, with shared scenes and objects to reduce appearance cues. Evaluation of 10 proprietary and 21 open-source Video-LLMs found Alignment is the primary bottleneck, with models often recognizing plausible semantics and local event progression but struggling with temporal alignment.

Hugging Face daily papers·Aug 31, 20:00 UTC · 16d agoAI research

25

The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding

Researchers introduced Brain2Semantics2Text, decoding sentence meaning from non-invasive MEG brain recordings via a semantic bottleneck, improving on prior Brain2Text methods.

The paper proposes Brain2Semantics2Text, a non-invasive speech decoding method that maps sentence-level magnetoencephalography (MEG) responses into a semantic embedding space and inverts those embeddings into natural language. Motivated by evidence that high-level semantic representations are distributed across cortex and evolve on slower timescales, the approach targets meaning rather than phonemes or words, avoiding the need for word-level alignment. The authors report improved sentence-level results compared to prior non-invasive Brain2Text methods despite the low signal-to-noise ratio of neural recordings.

Hugging Face daily papers·Sep 8, 20:00 UTC · 8d agoAI research2

25

Claude Fable 5.1 Solves the Cyphral Distich, a 370-year-old cipher

Claude Fable 5.1 solved Sir Thomas Urquhart's 370-year-old Cyphral Distich cipher, recovering a hidden royalist prayer for Charles II.

Vals AI reports that Claude Fable 5.1 solved the Cyphral Distich, a 64-number cryptogram from Sir Thomas Urquhart's Logopandecteision unsolved since 1653, in 44 minutes using 176k tokens with no human hints. The key insight was that the cipher's key was the book itself: each number indexes a word in the corresponding Proquiritation, taking the first letter, yielding 'O GOD UPHOLD KING CHARLS THE SECOND AND MAKE HIM THE SUPREME RULER OF THIS LAND'. The model also deciphered the larger Cyphral Octastich (285 numbers) from The Jewel (1652) using page-based word indexing, recovering all but nine letters of a royalist prayer. The puzzle had been listed among Klaus Schmeh's Top 50 unsolved encrypted messages.

Hacker News · AI·Sep 13, 21:06 UTC · 2d agoAI researchHN 63↑ · 6 comments1· 1 read

48

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification

VDiff-Bench, a 1,756-question benchmark, shows multimodal LLMs struggle with fine-grained image-difference identification, scoring as low as 8.7% on low-level changes.

VDiff-Bench is a multiple-choice benchmark of 1,756 four-way questions over image pairs covering 10 change categories including position, motion, color, texture, OCR/text and illumination, with curated hard negatives. Evaluation of 11 state-of-the-art open- and closed-source MLLMs shows fine-grained visual comparison remains brittle: 7-8B-scale open-source models score 52.5-70.6% on semantic changes but only 8.7-33.3% on low-level changes like noise and texture. Notably, Grok 4.3 shows a sharp performance drop on noise and texture differences, falling behind large open-source models like Kimi K2.5 and K3.

Hugging Face daily papers·Sep 4, 20:00 UTC · 12d agoAI research

32

How much of F-Droid is LLM generated?

A FOSS maintainer manually graded 102 F-Droid apps from the September 12, 2026 update batch, finding many show signs of LLM-generated code.

A student and FOSS app maintainer reviewed 102 apps pushed to F-Droid on September 12, 2026, assigning each a three-tier rating for likelihood of LLM-authored code (mostly AI >50%, hard to say/mostly human, no signs of AI). The heuristic relies on commit aesthetics, README and branding style, and the presence of agentic infrastructure like Claude Code or Codex, which automatically places an app in the 'mostly AI' tier. Example ratings include Amber (Nostr event signer) as mostly AI, and Aria for Misskey as showing no AI signs. The author stresses reliable detection of LLM-generated code from text alone is impossible, so ratings are approximate.

Hacker News · AI·Sep 15, 09:47 UTC · 1d agoAI researchHN 46↑ · 23 comments

15

Enoki: Efficient Multi-Level Hallucination Detection

Researchers introduce Enoki, an open information extraction framework unifying claim-level and span-level hallucination detection in LLMs at lower inference cost.

Enoki extracts text-anchored relational facts, verifies them against evidence, and projects unsupported facts back onto hallucinated spans, so claim-level verification and span-level localization share one representation without separate alignment. It supports LLM-based, encoder-based, and rule-based extraction regimes to balance accuracy against inference cost. Experiments show it stays competitive with strong claim-level systems while using fewer resources and outperforms them on fine-grained span- and entity-level localization. The authors also release EnokiQA, a dual-granularity dataset with aligned claim-level verification and span-level localization annotations.

Hugging Face daily papers·Aug 31, 22:21 UTC · 15d agoAI research

50

Technical Manual for a Toolkit for Measuring Contextual Individuation in Transformer Language Models

An open methodology toolkit measures whether transformer language models contextualize fixed word forms across domains using bridge forms and layer-wise silhouette analysis.

The manual documents an open toolkit built around 'bridge forms' - identical written words recurring across two or more subject domains with a different sense in each - to test whether transformer language models individuate word occurrences by context beyond the embedding layer. It covers declarative specification of bridge forms, Wikipedia corpus acquisition, occurrence localization, layer-wise representation extraction, domain-pairwise silhouette measurement, and visualization, justifying each choice against failure modes such as sense contamination and subword-tokenization misalignment. It is a methodological and implementation reference and reports no empirical results.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 16:38 UTC · 12d agoAI research

14

USN-8772-1: AOM vulnerabilities

Ubuntu USN-8772-1 patches four libaom flaws (CVE-2026-56208 to CVE-2026-56211) that could cause heap overflow, arbitrary memory writes, or code execution.

Ubuntu Security Notice USN-8772-1 fixes a heap buffer overflow in libaom's first-pass statistics buffer handling in Look-Ahead Processing mode (CVE-2026-56208), potentially causing denial of service or arbitrary code execution. Three additional flaws in spatial and temporal layer ID validation in the SVC encoder controls (CVE-2026-56209, CVE-2026-56210, CVE-2026-56211) allow arbitrary memory writes, out-of-bounds heap reads, or code execution. Users should apply the updated packages.

Ubuntu Security Notices·09:29 UTC · 10h agoAdvisoryCVE-2026-56208CVE-2026-56209CVE-2026-56210+1 CVEs

30

When Models Edit Too Much: On the Fidelity of Minimal Code Edits

A 400-task BigCodeBench evaluation shows frontier LLMs widely over-edit code; a preservation instruction cuts excess edits and raises Pass@1 by 2.3 points.

Researchers built an evaluation framework from 400 BigCodeBench problems with injected AST-level corruptions, each with a known minimal patch, to measure over-editing in LLM code repair. Even strong models like GPT-5.5 produce unnecessarily large edits despite high Pass@1. Adding a preservation instruction reduced average excess Levenshtein distance from 0.195 to 0.131, cut added cognitive complexity by 26.6%, and raised Pass@1 by 2.3 points. Reinforcement learning post-training gave the best out-of-domain edit-fidelity trade-off, while supervised fine-tuning overfit to seen corruption patterns.

Hugging Face daily papers·Sep 2, 20:00 UTC · 14d agoAI research1

30

WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data

WearableQA benchmark tests LLM health reasoning over longitudinal wearable data; the best of 14 evaluated LLMs reaches 72.9% accuracy.

WearableQA comprises 4,084 ten-option multiple-choice questions built from wearable time series, blood biomarkers, and demographics of 200 real users with up to 500 days of daily measurements. It defines 16 question types along two axes: data versus health reasoning, and single- versus cross-signal reasoning. Evaluation of 14 proprietary and open-source LLMs shows performance from 19.6% to 72.9% against a 10% chance baseline, with most models below 60%.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:52 UTC · 12d agoAI research

14