35 stories tagged with #hallucination, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Hallucination"
Stop Returning Text from RAG: The Typed Answer Contract That Prevents Hallucination
Enterprise Document Intelligence [Vol.1 #8A] - The schema is the contract: every field is a question the pipeline asks the model, and every answer is checkable The post Stop Return…
Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents
arXiv:2606.27806v1 Announce Type: new Abstract: World models for language agents come in two useful forms. An agent-based world model calls an LLM API and reasons flexibly in langu…
Hallucination in World Models Is Predictable and Preventable
An interactive web version of our study on hallucination in world models.…
Two New Large Libel Models Lawsuits, Though Alleging Mischaracterization Rather Than Outright Hallucination
They are, by my count, the 8th and 9th such claims filed in U.S. courts.…
KPMG pulls report on AI usage due to apparent hallucinations
Once again, AI proves to be an unreliable source of information about AI.…
A report on the benefits of AI was reportedly full of AI hallucinations
KPMG published a paper about the benefits of AI last year. An investigation found that it was full of AI hallucinations.…
KPMG report contained AI hallucinations on benefits of . . . AI
Bogus case studies on UBS and transit systems exaggerated adoption of the technology…
Ninth Circuit on AI Hallucinations
Some excerpts from today's long opinion in LNU v. Blanche, decided by the Ninth Circuit by Judge Richard Paez, Carlos……
Ernst & Young published cybersecurity report full of hallucinations
An investigation into fabricated citations and broken references in EY's "Points of Attack" cybersecurity report on loyalty system fraud.…
Automatic Layer Selection for Hallucination Detection
Recent studies on hallucination detection have shown that hallucination-related signals are more strongly encoded in intermediate layers than in the final layer of large language m…
Stop traumatizing AI into loops and turn hallucinations into an honest "I don't know!" by being NICE to them (Proof of Concept, Research, I don't want to sell anything)
OpenAI admits AI hallucinations are mathematically inevitable (Sept. 2025)
In a landmark study, OpenAI researchers reveal that large language models will always produce plausible but false outputs, even with perfect data, due to fundamental statistical an…
Beyond Final Answers: Auditing Trajectory-Level Hallucinations in Multi-Agent Industrial Workflows
Large Language Models (LLMs) are increasingly deployed as autonomous agents that reason, use tools, and act over multiple steps. Yet most hallucination benchmarks still evaluate on…
Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration
The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to…
Sonnet hallucinated. My agent stored it as fact.
I thought my AI agent had been hacked. Four days later I pulled the SQLite database and found something stranger — it had poisoned its own memory.…
Preventing GPT hallucination in automated content pipelines: how I structure Make.com flows with data injection
I run a Make.com pipeline that produces daily sports betting articles. Odds API in, API-Football in,...…
Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood. Existing interpretability wo…
CHASD: Language Increment-Calibrated Contrastive Decoding against Hallucination in LVLMs
Large Vision-Language Models have shown strong multimodal reasoning capabilities, yet they remain susceptible to object hallucinations when language priors dominate insufficient or…
AI hallucinations are infiltrating expert work—and entering the permanent body of knowledge
A Columbia researcher who studies AI nearly published a study with a hallucinated reference himself. He's not alone.…
I built an AI-based clinical prescription scanner (Next.js/Groq). Lessons learned on RAG hallucination and data mapping.
AI Agent Failure Modes Beyond Hallucination
AI can make mistakes, models hallucinate, models make stuff up - those are well-known complaints. Yet...…
Leroy's elusive little people: A review on lilliputian hallucinations (2021)
Hallucination as Exploit: Evidence-Carrying Multimodal Agents
Multimodal agents use screenshots, documents, and webpages to choose tool calls. When a false visual claim triggers a click, email, extraction, or transfer, hallucination becomes a…
Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination
Modality-conflict hallucination occurs when multimodal large language models (MLLMs) prioritize erroneous textual premises over contradictory visual evidence. To understand why vis…
Grounding LLMs with Fresh Web Data to Reduce Hallucinations
Why production LLM systems need live web search to overcome knowledge cutoffs and stale training data…
How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study
While AI-generated hallucinations pose considerable risks, the underlying cognitive mechanisms by which humans can successfully recognize or be misled by these hallucinations remai…
TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction
Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor uniformly less trustworthy. Yet …
LLM Evals Are Based on Vibes — I Built the Missing Layer That Decides What Ships
Most LLM evaluation systems rely on vague scoring and human judgment disguised as metrics. I built a lightweight evaluation layer in pure Python that turns LLM outputs into reprodu…
Reducing LLM Hallucinations in 2026: LoRA, F-DPO, and the Math That Actually Works
It is May 2026, and the field has stopped pretending hallucinations are going to disappear. What...…
The cracked mirror: why AI hallucination is structural, not a bug
There is a particular kind of error a language model makes that feels different from every other kind...…
TypedMemory – long-term memory and reflection for AI agents
TypedMemory. Contribute to canis-minor/typedmem development by creating an account on GitHub.…
Most LLM Failures Aren’t Hallucinations — They’re Structural Reasoning Failures
Most LLM Failures Aren’t Hallucinations — They’re Inherited Assumptions
EY retracts study after researchers discover AI hallucinations
The Uncanny Horror of AI Hallucinations (2025)
Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.…