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

ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation

This solves a real RAG problem: one-size-fits-all chunking and retrieval fails when your corpus is heterogeneous. The idea of semantic clustering over questions and learning per-cluster configurations is straightforward and practical. For builders running RAG on large, domain-specific corpora, this is worth evaluating. The trick is whether the upfront cost of building cluster-specific indices pays off in retrieval quality.

arXiv cs.CLPaper

CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering

This is the missing piece for production RAG: runtime validation that detects when the system is about to hallucinate and either fixes it or refuses to answer. The numbers are from controlled domains, but the architecture is general. If you're shipping RAG systems into regulated spaces like legal or compliance, this approach to grounding and citation validation is now table stakes.

arXiv cs.CLPaper

REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving

RAG latency is now a solved problem in principle. This work shows that compression gains are unstable across queries and that the old post-retrieval approach is adding overhead without benefit. REVA mines your own traffic to build a scoring layer that's specific to your generator and documents. If you're running knowledge-intensive applications at scale, this is worth implementing before optimizing the retrieval layer itself.

arXiv cs.CLPaper

FlexComp: One Model for Every Ratio in Context Compression

Context compression just became more practical. Existing compressors require separate models for each ratio and apply uniform compression regardless of input complexity, both wasteful. FlexComp trains once and compresses flexibly, with routing that preserves 98% accuracy at extreme compression. This is infrastructure that RAG and agent builders should test immediately—it removes a deployment friction point.

arXiv cs.LGPaper

Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)

Text-to-SPARQL is the bridge problem between natural language and structured knowledge graph queries. The paper shows that off-the-shelf LLMs plus good prompt context (schemas, samples) can hit 41.9% exact-match on execution without fine-tuning, which is meaningful. For builders adding conversational KG access to products, this is a usable baseline. The finding that larger general-purpose models outperform code-specialized ones is worth noting.

arXiv cs.CLPaper

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

The token-efficiency angle is concrete and relevant: RAG systems routinely spend 60-80% of tokens on structural context, and your costs scale with query volume. VikingRAG's directory-aware design and experience-edge reuse show real cost reductions. If you're operating a production RAG pipeline on structured documents, this is worth modeling against your actual token spend.

arXiv cs.AIPaper

PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving

The innovation is treating perceived latency as the quality metric, not just raw latency, and using filler to manage user experience while waiting for better answers. Deployed on a robot sales chatbot and showing real improvements. If you're building production RAG systems, the cascading routing and cache strategies are usable. The paper is dense on mechanisms but the practical payoff is there.

arXiv cs.CLPaper

The Answer Path and the Grounding Instruction in LLM Question Answering over Knowledge Graphs

Useful guidance for building graph RAG pipelines, though the findings are somewhat incremental: of course including the answer path matters. The precision-recall insight is the meaty one. If you're tuning graph RAG systems, focus your retrieval effort on recall, not on cleaning noisy triples. The grounding instruction section is underexplained here, so check the full paper if that's your bottleneck.

arXiv cs.CLPaper

LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation

This is actionable. If you're running GraphRAG or similar systems and paying for repeated LLM calls during retrieval, LiteRAG's algorithmic approach can cut costs dramatically. The benchmarks are limited to two datasets but the wins are large enough that it's worth testing on your own retrieval problem. The key insight: don't use an LLM to explore the graph if you can compute it.

arXiv cs.CLPaper

KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

This matters if you're serving RAG or agent systems at scale. Standard KV cache reuse only works when context matches exactly; these methods extend it to retrieved chunks and agent-written text. The measured wins are real: 100x latency, 99% cost reduction. If your LLM serving costs are high, investigate whether your retrieval system can use these techniques.

arXiv cs.CLPaper

ReCite: Agentic Reasoning for Faithful Citation

This tackles hallucination at a specific layer: citation generation. The insight is solid—semantic similarity fails when the paper is real but doesn't actually support the claim. The agent-based verification loop is the real contribution. For builders using RAG for research or writing tools, this is a pattern worth stealing: decouple search from verification, let the agent reason about fit.

arXiv cs.CLPaper

Record Grouping Controls Evidence Weight in Language Models

The finding is concrete: the way you package retrieved information into evidence chunks changes model output in measurable ways. This applies directly to RAG systems and any LLM system consuming structured data. If you're building search-augmented LLM products, test whether your chunking and grouping strategy introduces systematic biases in downstream decisions.

arXiv cs.CLPaper

What the Window Does Not Contain: Auditing Provenance in a Document-Grounded Instability Benchmark

The core finding is important for anyone evaluating document QA systems: instability can come from the benchmark itself, not just model flakiness. An LLM that wobbles on evidence it was not shown is not failing to reason, it is failing to admit the evidence is absent. This is a methodological lesson that affects how you validate and trust RAG and document retrieval systems in the wild. Clean your test sets before you ship.

arXiv cs.CLPaper

Building Trustworthy Graph-Agentic RAG for Social Good: Architectures, Failure Propagation, and Assurance by Construction

This maps a real architectural problem: when agents traverse knowledge graphs and delegate tasks, failures compound. The paper is useful for anyone building agent systems where authority, traceability, and recourse matter—think social services, health, or legal domains. For most commercial RAG, it's more thorough than necessary, but if your users need to audit why the agent did something, this taxonomy of failure chains is worth studying.

arXiv cs.CLPaper

Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection

The core insight is that LLMs can use symbolic reasoning (SQL) to validate their own outputs without explicit supervision. This is a practical technique for RAG and retrieval-grounded workflows where the reference material is structured. Not a paradigm shift but a useful pattern to test against your hallucination detection baseline.

arXiv cs.CLPaper

NS-ST-GraphRAG: Neuro-Symbolic Spatio-Temporal GraphRAG for Literary Knowledge Processing

The problem is real: classical texts have answers that depend on when and where events happen, and standard RAG fails at that. The solution is technically sound, but the benchmark itself (Red-Chamber-QA) is the more useful contribution. For builders working on document understanding or long-form reasoning, the spatio-temporal graph structure could transfer. The literary domain keeps it niche.

arXiv cs.CLPaper

Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG

Context compression via learned embeddings is practical and the numbers are significant. Training on both correct examples and failure cases is a straightforward but under-deployed technique. If you're running RAG systems in production and watching token costs, this is worth testing. The 4-24x speedup range suggests it's sensitive to retrieval depth and model size.

arXiv cs.CLPaper

How Much Do Legal RAG Systems Still Hallucinate?

This is a reality check on production RAG in a domain where mistakes have real consequences. The finding that no system is uniformly good, and that false-premise questions break even the best ones, matters if you're deploying legal AI. The lesson: RAG alone doesn't solve hallucination in law. You need a human loop or a classifier that catches the bad cases, and this paper gives you a baseline to test against.

Hacker News (AI, 50+ points)Article

Three sites made 215,128 “best software” pages for AI. Perplexity cites them

This is SEO poisoning at scale, and it works because RAG systems citation-wash thin or fabricated content. For builders shipping search or recommendation products: you're running the engine that legitimizes this. The incentive structure is broken. For anyone relying on AI-generated recommendations, treat them as starting points, not ground truth. Perplexity's citation problem is everyone's problem now.

arXiv cs.CLPaper

Incremental Pooled LLM Evaluation for Cost-Effective Retrieval Model Selection

Practical tooling for building production RAG systems. Instead of getting fresh relevance judgments for every retrieval candidate you want to test, you pool documents and judge only the new ones each time, reusing labels. They hit 97% consistency with gold-standard rankings and cut judgment work by 65-80%. If you're doing retrieval model selection at scale, this method cuts a real cost in your evaluation loop.

arXiv cs.CLPaper

Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAG

This hits a real problem in RAG marketplaces: how does a data provider verify they're being paid for their corpus? DirBucket's approach is clever, embedding secret directions in paraphrases to survive the generator's rewriting. The method is provider-side, which is tactically useful. This matters most if you're building a RAG platform with multiple data sources or licensing models, or if you're a data provider worried about unauthorized reuse. Not mainstream yet, but the problem is getting sharper.

arXiv cs.AIPaper

Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents

This is deployment craft: after compression, bigger doesn't mean better, so pick sub-networks by what actually works on the hardware you have. The weight-sharing supernetwork keeps selection cheap. It's useful for anyone shipping to constrained devices, but the context is narrow: factory documentation retrieval. The real insight is transferable though: test on the real hardware, not the lab benchmark.

arXiv cs.LGPaper

CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation

RAG is a trust boundary that most teams haven't hardened. If a developer toolkit pulls in code snippets from a repository, an attacker can poison those snippets to influence generated code without touching the model. This is a real threat for any codebase connected to public or semi-public knowledge sources. For teams building RAG-based development tools: you need artifact validation and provenance tracking before this becomes the exploit of choice.

arXiv cs.CLPaper

Improving Health Literacy through Lay Summarization of Radiological Reports: An Evaluation of BioNER and Retrieval-Augmented Generation

This is a solid applied NLP paper addressing a real problem: patients need to understand their medical records, and hallucination in ungrounded LLM summaries is dangerous. The combo of NER plus RAG is straightforward but works. If you're building healthcare NLP tools, this framework is worth adopting. Otherwise, it's domain-specific.