Search: “LLMScore”

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

Guiding Worker Self-Selection in Crowdsourcing Contests: An LLM-Augmented Algorithmic Approach

Researchers introduce GRAF, a greedy framework for crowdsourcing contest self-selection, and LLMScore, an LLM-driven method that auto-designs its scoring algorithm.

The paper studies self-selection in Tullock contests (SSTC), where workers choose contests and then compete within them. GRAF is a greedy polynomial-time framework that orders workers by a score vector with zero worker regret and platform optimality guarantees in special cases. LLMScore is an LLM-driven evolutionary framework that produces human-readable, inspectable scoring code, jointly optimizing platform utility and worker satisfaction. Across 1,000 synthetic instances in four settings, GRAF with LLMScore achieves high-quality, often near-optimal outcomes with low worker regret, transferring from small training instances to larger, structurally different settings.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 16:51 UTC · 8d agoAI research1

22

llm 0.34

Version 0.34 of Simon Willison's llm CLI adds response-duration metrics to log output, plus bug fixes and faster log querying.

The open-source llm command-line tool for interacting with large language models released version 0.34. The headline change adds response duration in milliseconds and human-readable form to llm logs --usage Markdown output, plus a new duration_ms field in llm logs --short. The release includes several contributed bug fixes and a significant performance improvement to llm logs, alongside the related llm-openrouter 0.7.1 release.

Simon Willison·Sep 2, 19:23 UTC · 13d agoAI tools & infra1

28

When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control

Chain-of-Self-Questioning prompting cuts LLM wrong-answer commitments 32% relative while raising answered accuracy, holding across eleven model families.

The paper introduces Chain-of-Self-Questioning (CoSQ), a prompt-only framework that makes LLM answer commitment conditional on an explicit assessment of the information required to answer. On an 817-item TruthfulQA multiple-choice set, Grounded-CoSQ at τ=0.90 reduced mean unconditional wrong-commitment rate from 13.1% under chain-of-thought to 8.9% (a 32.1% relative reduction), while raising answered accuracy from 86.9% to 89.7% at 87.6% coverage. Improvements held across eleven open-weight and hosted model families and at every evaluated threshold, with convergent evidence from a Natural Questions short-answer evaluation.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 17:52 UTC · 21h agoAI research

30

LLMs and Contextual Integrity

Bruce Schneier highlights two papers: the CIMemories benchmark shows frontier LLMs leak memory attributes up to 69%, and an RL method reduces inappropriate disclosures.

Bruce Schneier discusses contextual integrity in LLMs, referencing the CIMemories benchmark, which uses synthetic profiles with 100+ attributes per user to test whether models with persistent memory disclose sensitive information appropriately. Evaluation showed frontier models exhibit up to 69% attribute-level violations, with GPT-5's violation rate rising from 0.1% to 9.6% across 40 tasks and reaching 25.1% with repeated prompting, showing unstable leakage behavior. A second paper introduces a reinforcement learning framework trained on a synthetic 700-example dataset that substantially reduces inappropriate disclosure while maintaining task performance, with improvements transferring to the human-annotated PrivacyLens benchmark.

Schneier on Security·Aug 18, 10:40 UTC · 29d agoAI safety & security

48

xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems

xDailyBench tests 11 frontier LLMs on 248 real-life consultation tasks; the best models score 75.6% and lag on implicit requirements.

The benchmark spans 51 scenarios across personal life, white-collar work, learning and research, and cross-domain activities, grounded in requests users actually completed or intended to complete with AI. Tasks are scored with fine-grained binary rubrics covering explicit and implicit requirements under standardized agentic settings. Across 11 frontier models, the best achieved a 75.6% task-level score, with all models performing at least 9 percentage points worse on implicit than explicit requirements.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:30 UTC · 8d agoAI research

26

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 · 6d agoResearch1

32

Training a 3.8B LLM to 0.384 CORE for $998 – Hugo Vergnes

Independent developer Hugo Vergnes trained a 3.8B-parameter Llama-style model to 0.384 CORE on 65B tokens for $998 in 43 hours on rented B200s.

Hugo Vergnes trained little-lm, a 3.848B-parameter decoder-only LLM, on 65.3B tokens in 43 hours for $998 using rented NVIDIA B200s, scoring 0.384 on the CORE benchmark and beating nanochat d32 (0.310) at similar cost. The Llama-style architecture uses RMSNorm, RoPE, GQA with 24 query and 8 KV heads, relu-squared MLPs, QK-norm, and ResFormer-style value embeddings that account for 19% of parameters. Key wins included the Muon optimizer for matrix parameters, a trapezoidal learning-rate schedule with linear cooldown, FP8 training plus vocabulary padding for roughly 33% throughput gains, and the ClimMix dataset over FineWeb-Edu. The project, inspired by Karpathy's nanochat, was built as a config-driven YAML framework for small LLM training.

Hacker News · security·Sep 10, 02:04 UTC · 6d agoAI researchHN 28↑ · 2 comments1

35

VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities

Introduces VEX-Bench, 75 expert-labeled real-world cases testing whether LLM agents can assess supply chain vulnerability exploitability; frontier models reach about 80% F1.

VEX-Bench is the first benchmark evaluating LLM agents on assessing whether upstream dependency vulnerabilities are exploitable in downstream projects, with 75 real-world expert-labeled cases across Python, Java, and Go mined from GitHub. Nine models across three agent harnesses were evaluated; GPT-5.5 and Claude Opus 4.6 reach approximately 80% F1 on binary vulnerability-status classification, but only GPT-5.5 surpasses 70% macro-F1 on fine-grained justification classification. The gap highlights the difficulty of moving beyond binary exploitability calls to explaining exploitability reasons, unlike prior benchmarks targeting zero-day settings.

arXiv cs.CR·Sep 7, 22:52 UTC · 8d agoResearch1

42

When the prompt becomes the payload: A practical pen-testing guide for GenAI, LLM and RAG applications

CSO Online publishes a practical penetration-testing guide for GenAI, LLM, and RAG applications, covering prompt injection, retrieval poisoning, and tenant isolation testing.

The guide frames LLM applications as attack graphs spanning prompts, retrieval layers, vector stores, tools, identities, and downstream APIs, arguing that conventional web testing misses instruction-vs-data channel risks. It builds on OWASP prompt injection guidance (direct vs. indirect injection) and NIST's 2025 adversarial machine-learning taxonomy, noting that RAG and fine-tuning do not remove injection risk. Recommended practices include documenting trust transitions across components, using canaries and synthetic records to avoid test side effects, running multi-turn and obfuscated injection campaigns, and verifying chains from poisoned documents to observable state changes. It also details testing RAG pipelines via controlled document poisoning across metadata, OCR layers, and code comments, plus cross-tenant isolation checks on retrieved document IDs.

CSO Online·Sep 9, 10:00 UTC · 7d agoAI safety & security1

28

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

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 · 15d agoAI research

25

IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications

IdeaAMBIG benchmark of 660 specification-gap instances shows LLMs localize implementation-critical research gaps poorly, with best model at 9.6% defect recovery.

IdeaAMBIG is a benchmark of 660 evidence-grounded instances evaluating whether research-method specifications provide enough information for faithful implementation: 163 real-world gaps from reproducibility reports and GitHub issues plus 497 controlled synthetic gaps. It tests codification-readiness assessment, defect localization, and clarification action generation across 13 LLMs. The best model achieves only a 9.6% Macro Defect Recovery Rate on real-world instances, though 80.6% clarification success when given the annotated defect, and an oracle study shows gold resolutions raise codification-ready rates from 14% to 98%. Defect localization emerges as the main bottleneck across all evaluated models.

Hugging Face daily papers·Sep 8, 20:00 UTC · 7d agoAI research

30

BenchMIRT: What are LLM benchmarks actually measuring?

AllenAI's BenchMIRT blog post examines what LLM benchmarks actually measure and their reliability.

AllenAI published a Hugging Face blog post introducing BenchMIRT, which investigates what large language model benchmarks actually measure. No article text is available, so specific findings, methods, or benchmark scores cannot be extracted. The work appears to target benchmark validity, a live concern for model evaluation and comparison.

Hugging Face Blog·Sep 1, 21:39 UTC · 14d agoAI research

38

Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs

Attack shows unaligned orchestrators can launder capabilities from aligned frontier LLMs via benign subtask consultation, raising Gemma-4-31B CBRN rubric score from 62.3 to 83.1.

The paper introduces capability laundering, where a weaker unaligned model decomposes a harmful task into benign-looking subproblems, queries a stronger aligned model on each, and recombines answers locally, bypassing per-interaction safety evaluations. Evaluation used GPT-5.5, Claude Opus 4.8, and Grok-4.3 as consultants to four local orchestrators on CyBench, BountyBench, and CBRN tasks. On CyBench, Gemma-4-31B recovered 8/14 candidate tasks with GPT-5.5 and 7/9 with Opus, while Muse-Glimmer-30B recovered none. Across an eight-step hypothetical bioweapon attack chain, consultation raised Gemma-4-31B's mean rubric score from 62.3 to 83.1, exposing a gap in defenses that only refuse complete harmful tasks.

arXiv cs.CR·Sep 14, 11:10 UTC · 2d agoAI safety & security

55

IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications

IdeaAMBIG benchmark with 660 instances measures whether LLMs can spot and fix underspecified research-method details for faithful implementation.

Researchers introduce IdeaAMBIG, a benchmark of 660 evidence-grounded instances (163 real-world gaps from reproducibility reports and GitHub issues, 497 controlled synthetic gaps) built from papers, codebases, and reproduction artifacts. It evaluates codification-readiness assessment, defect localization, and clarification action generation. Across 13 LLMs, the best model achieved only 9.6% Macro Defect Recovery Rate on real-world instances but 80.6% clarification success when given the annotated defect. An oracle study showed gold resolutions raise the codification-ready rate from 14% to 98%, identifying defect localization as the main bottleneck.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 17:59 UTC · 6d agoAI research2

28

Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States

Researchers propose auditing LLM bias via relative hidden-state representations, detecting bias increases with 3-50x less compute than output-level benchmarks.

The paper introduces a reference-based bias auditing method that compares hidden-state representations across model variants, such as before and after fine-tuning, by encoding sentences relative to a fixed anchor set. The resulting Representational Bias Shift (Delta-B) correlates with output-level bias change in 15 of 18 tested settings, reaching |r| = 0.84 under full fine-tuning across WildGuardMix, DecodingTrust, and ToxiGen benchmarks. Thresholding Delta-B detects checkpoints whose bias increased with ROC AUC between 0.65 and 0.99 and beats a SEAT-based baseline, while auditing a model in about three minutes with 3-50x less compute.

Hugging Face daily papers·Sep 8, 20:00 UTC · 7d agoAI research

42

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

Benchmark Scores Are Pipeline-Dependent: A Reliability Audit of Cybersecurity LLM Benchmarks

Audit of eight cybersecurity LLM benchmarks shows evaluation pipeline choices can swing scores by over 80 points and reshuffle most model rankings.

Researchers modeled eight cybersecurity benchmarks as configurable measurement pipelines and audited 10 proprietary, open-weight, and cybersecurity-specialized LLMs. They identified 15 systematic failure modes and showed a single pipeline choice can change a model's score by more than 80 percentage points and alter rankings; semantically similar task pairs rank the same models differently. Under a standardized harness, nine of 10 models shifted at least three ranks on at least one benchmark, motivating pipeline-aware auditing for reliable model evaluation.

arXiv cs.CR·Sep 8, 14:01 UTC · 8d agoAI research1

42

LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys

Schema-aware split learning uses LLaMA-3.2-3B-Instruct as shared semantic encoder to harmonize heterogeneous mental-health surveys while raw data stays local.

The paper proposes a schema-aware split learning framework where an LLM serializes heterogeneous mental health survey records into natural language and is fine-tuned via LoRA, partitioned across client and server. Clients keep raw survey responses local and run only a lightweight front-end while the resource-intensive backbone runs server-side. Using LLaMA-3.2-3B-Instruct, the framework attains an average ANLS of 0.708 with 2,000 training samples, beats federated learning in eight of nine settings, and cuts per-client computation by three orders of magnitude while generalizing to unseen datasets.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 16:59 UTC · 1d agoAI research

18

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 · 7d agoAI research

30

Retrofitting Code Using LLMs to Support Exceptional Behavior

EXCODER combines static/dynamic analysis with LLMs to retrofit exception-handling code, achieving 85.92% pass@1 with Qwen 2.5 Coder 32B on Java benchmarks.

The paper introduces the task of retrofitting existing code with Exception Related Code (throw statements, guarding conditions, try/catch blocks) so that given Exceptional Behavior Tests pass. EXCODER performs context engineering by integrating static and dynamic program analysis output with LLMs; it was evaluated on a benchmark built from 304 methods across 75 GitHub Java projects. Combined with Qwen 2.5 Coder 32B, EXCODER achieves pass@1, 5, and 10 rates of 85.92%, 86.18%, and 86.51%, roughly 13 percentage points over baseline, and manual inspection reveals remaining limitations.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 16:18 UTC · 6d agoAI research1

25

CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

CS-Guard benchmark shows LLM code-generation guardrails fail widely, with ~50% jailbreak ASR text-to-code and up to 100% code-to-code.

Researchers introduce CS-Guard, the first systematic benchmark for evaluating LLM guardrails for code generation security, covering text-to-code (1,000 malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack) and code-to-code (331 prompts across infilling, completion, and translation). They evaluate 9 guardrails across seven LLMs, finding average jailbreak attack success rates around 50% for text-to-code and 14.4% to nearly 100% for code-to-code. The fictional scenario attack achieves ASR close to 100% across many guardrails, raising reliability concerns for real-world software development. The benchmark and data are released publicly.

arXiv cs.CR·Sep 9, 06:50 UTC · 7d agoAI safety & security1

45

What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation

A new benchmark shows LLMs reach 68.3-93% accuracy propagating local revisions across conversationally generated artifacts, with parallel-sample selection most cost-effective.

The paper introduces a benchmark for revision propagation: when users request a local change, LLMs must identify dependencies and update all affected parts of an artifact generated through conversation, where context lives in the chat history. Nine revision methods, including sequential reflection and parallel sampling variants, were evaluated on gpt-oss-20b/120b, gpt-5.4-mini, and qwen3.5-9b/27b/122b. Baselines scored 68.3-93% accuracy, and selecting among three parallel samples via LLM-based or medoid selection improved accuracy by 2.2-9.7% as the most cost-effective test-time compute strategy. Code and dataset are released.

Hugging Face daily papers·Sep 2, 20:00 UTC · 13d agoAI research

30

You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs

Study quantifies DPO-tuned LLMs undershooting requested emotional intensity, tracing the gap to candidate-pool extremity rather than conditioning format.

Conditioning an instruction-tuned LLM on continuous valence-arousal targets yields gain of only 0.26 for valence and 0.13 for arousal on Llama-3.1-8B, far below faithful control of 1.0. The authors attribute undershoot to neutral-heavy preference corpora like EmoBank and candidate pools lacking extreme affect, leaving DPO without extreme exemplars. Uniform target coverage with a hotter candidate pool raises valence gain to 0.40 on Llama-3.1-8B and 0.44 on Qwen3-8B, with modest in-distribution cost; arousal gains remain unstable across seeds.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:47 UTC · 8d agoAI research

31

llm-openrouter 0.7.1

Simon Willison released llm-openrouter 0.7.1, a performance fix for loading OpenRouter models in his LLM CLI plugin.

Version 0.7.1 of the llm-openrouter plugin addresses a performance problem when loading OpenRouter models in the LLM command-line tool. The fix was contributed by GitHub user waveplate. It is a minor maintenance release with no security implications noted.

Simon Willison·Sep 2, 20:23 UTC · 13d agoAI tools & infra

14

Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence

New framework tests whether LLM-cited explanation factors are necessary or sufficient, finding weak correlation across Claude, GPT, and Gemini models.

An arXiv paper introduces black-box intervention tests measuring whether factors LLMs cite in their explanations are necessary or sufficient for their outputs in agent oversight workflows. Across eight models from the Claude, GPT, and Gemini families, Spearman correlations between cited rankings and measured influence ranged from 0.349-0.354 (advisor recommendation) to 0.431-0.580 (prompt monitoring). Uncited factors scored above the lowest cited factor in up to 57.6% of advisor responses, showing cited top-three factors do not reliably identify the most influential inputs.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 17:37 UTC · 11d agoAI safety & security1

44

Towards Tackling Application Logic Flaws through Autonomous Formal-Logic Modeling and Automated Reasoning

LL-Verifier combines LLMs with logic model checking to automatically discover logic flaws, uncovering vulnerabilities in 27 IoT access-control protocols.

Researchers present LL-Verifier, a framework that uses LLMs to autonomously convert natural-language protocol descriptions and security goals into formal logic models in a new logic language built on Maude, then applies logic model checking for exhaustive verification. The framework targets application-logic flaws that are tied to business semantics and hard to scale with manual analysis. Evaluation on 27 access-control protocols of widely used IoT devices uncovered a range of sophisticated logic vulnerabilities with security and privacy implications.

arXiv cs.CR·Sep 9, 17:58 UTC · 6d agoResearch1

42

Large Language Models for HVAC Operations in Building Energy Systems: A Critical Review of Methods, Applications, and Deployment Readiness

Systematic review of 66 studies finds LLMs for HVAC operations are mostly research-stage, with no ready-now deployment and only four pilot-level studies.

A critical review of 66 peer-reviewed studies from 2023 to March 2026 examines LLMs for HVAC operations in building energy systems. Only four studies reach pilot-level evidence, none reports sustained operational deployment, and 63 of 66 are research-only. Conventional ML, MPC, and RL remain dominant for high-frequency control and short-horizon forecasting, and the evidence supports LLMs primarily as semantic and workflow layers rather than autonomous controllers.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 16:08 UTC · 11d agoAI research

45

When LLM Decompilers Recompile More and Preserve Less

Researchers show LLM decompiler outputs can recompile yet diverge behaviorally, proposing the Decompile-Diverge fuzzing oracle to catch hidden changes.

The paper demonstrates that LLM-based decompilers can produce code that recompiles and passes all shipped tests yet diverges on other legitimate inputs—4.9% overall and up to 13% for one system—and can make disclosed vulnerabilities vanish without a visible crash. Across 300 real GitHub functions and 287 CVE-grounded functions, a refinement LLM lifted Ghidra's build rate from 75% to 90% while Matched rate fell from 74% to 62%, with up to one tenth of vulnerabilities showing Crash Absence. Decompile-Diverge detects these gaps by synthesizing drivers, growing fuzzing corpora from the reference, and rerunning decompiled code on identical inputs.

arXiv cs.CR·Sep 4, 17:16 UTC · 11d agoResearch

42

llm-gemini 0.34

llm-gemini 0.34 adds support for Google's new Gemini 3.8 Flash model with configurable low, medium and high thinking levels.

Simon Willison released llm-gemini 0.34, a plugin for the LLM CLI that adds the gemini-3.8-flash model, including low, medium and high thinking levels, and fixes an issue where async responses failed to record the resolved model version. The release coincided with Google's launch of Gemini 3.8 Flash, plus a Gemini 3.8 Flash Cyber variant restricted to trusted defenders. Willison noted the Flash tier's speed, low cost and competence at HTML and JavaScript generation tasks.

Simon Willison·Sep 2, 16:39 UTC · 13d agoAI tools & infra

30

What researchers learned about building an LLM security workflow

Oslo and FFI researchers show structured agentic workflows lift LLM alert-triage accuracy from 0% to about 93% on malicious cases.

Researchers at the University of Oslo and the Norwegian Defence Research Establishment tested GPT-5-mini, Claude 3 Haiku, Qwen3:30B, and Gemma 3:27B on alerts from the AIT Log Data Set V1.1; given only alert descriptions and log summaries, all four models correctly flagged zero percent of true-positive cases involving reconnaissance, brute-force logins, and initial access. Wrapping the same models in a workflow with constrained SQL queries over Suricata logs, an evidence summarizer, and a verdict stage with revision loops raised malicious-case accuracy to an average of 93 percent, with GPT-5-mini identifying every malicious case across 100 runs. The authors flag it as a proof-of-concept on one synthetic scenario and note models skewed conservative on benign alerts, with GPT-5-mini marking every benign case uncertain.

Help Net Security·Aug 24, 04:21 UTC · 23d agoAI research1

55