ArtificialIntelligence.io

The Signal

Everything that matters in AI, with our take.

Updated through the day. Every headline links straight to the source. The two lines underneath are ours.

arXiv cs.AIPaper

From Citations to Contributions: LLM-Assisted Credit Scoring of Research Articles

This is solid academic work on an unsolved problem: citation systems treat all references as equally important, which understates how much a paper owes to incremental steps versus fundamental breakthroughs. The LLM-as-comparator approach is pragmatic, though the scalability story stops at experiments. Real value emerges if this ships in research tools, but that's a product problem, not a research problem. For most builders, this stays theoretical unless your system needs to surface influence accurately.

arXiv cs.CLPaper

Decomposing LLM-Judge Uncertainty to Target Expert Labels

The insight is real: knowing whether an LLM judge is ignorant versus whether experts genuinely disagree changes where to spend labeling budget. But the practical payoff depends on your labeling setup. If you're already running LLM judges at scale and can afford Bayesian decomposition, this tightens your data collection. Otherwise it's an optimization on a workflow most teams haven't yet built.

arXiv cs.AIPaper

Automated Vulnerability Injection in Smart Contracts Using Large Language Models

The practical yield is low (16.58% survival rate), and surviving vulnerabilities cluster in simple structures, which limits the approach's scope. For security teams building on-chain, this signals that LLM-assisted fuzzing of contracts is still immature. The real value here is methodological: if this pipeline matures, continuous synthetic vulnerability generation could become part of standard contract testing, but we're not there yet.

arXiv cs.CLPaper

PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation

The feedback loop itself is the insight here: structured critique from an evaluator LLM outperforms raw iteration. If you're generating synthetic data at scale for model training or testing, this pattern (generate-evaluate-revise) is more efficient than hoping longer context or few-shot examples solve it. Worth testing against your own data pipelines.

arXiv cs.CLPaper

Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift

A needed benchmark that surfaces a real gap: most text-to-SQL work measures final query correctness, not whether the model tracks the conversation or recognizes when users change their minds. The patterns tested are genuine: users ask imprecise questions that need clarification, then they retract. If you're building database interfaces with LLMs this shows where models break. The evaluation of 12 models is useful for positioning.

arXiv cs.CLPaper

How You Ask Shapes What You Get: A Theory-Seeded Measurement of Articulation in Advice-Seeking LLM Conversations

The insight is that how users articulate their request matters as much as the request itself, and this structure is invisible to topic-based evals. There's one recurring style worth noting: long-form but information-poor. This is useful for understanding why the same topic generates different model outputs, but the actionability for builders is limited. Most teams will incorporate this into eval design, not product.

arXiv cs.CLPaperClaude Watch

Chain-of-Experience for Continual LLM Improvement

This is a real signal for anyone running agent pipelines: test-time experience accumulation beats zero-shot prompting consistently across math, coding and knowledge tasks, and it's cheaper, not just better. If you're paying per-call for agent loops, building in a lightweight experience-replay mechanism is a concrete lever worth testing against your current baseline this quarter.

arXiv cs.CLPaper

Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity

The finding that matters is the disconnect between what a model internally knows about its own uncertainty and what it actually outputs. It suggests hallucination on rare entities isn't a knowledge gap so much as a generation-time calibration failure, which means steering or decoding-time interventions could plausibly fix a chunk of it without retraining. Worth tracking for anyone building factuality guardrails or RAG confidence scoring.

arXiv cs.CLPaper

LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs

This quantifies something every engineer using coding assistants has already noticed anecdotally. The finding that models sometimes fabricate justifications for choosing Python after the fact is the more interesting result, it's a small but concrete example of post-hoc rationalization in code-gen reasoning traces. Worth a glance if you're evaluating coding agents for polyglot codebases.

arXiv cs.CLPaper

Poli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts

This lands squarely on a problem enterprises deploying LLMs for legal or policy analysis already worry about quietly. The five-dimension decomposition is more useful than a single bias score because it tells you where the disparity actually shows up, in framing versus judgment versus legal reasoning. Worth a look if you're building anything touching geopolitics, compliance, or news summarization, but this is a measurement tool, not a fix.