This canonical paper page includes Commercialization Proof and Related Resources.
ARXIV:2605.13829 · LLM SAFETY · SUBMITTED 14 MAY · 20:10 UTC · FRESHNESS FRESH
ARXIV:2605.13829LLM SAFETYSUBMITTED 14 MAY · 20:10 UTCFRESHNESS FRESHHarry Mayne · Lev McKinney · Jan Dubiński · Adam Karvonen · James Chua · Owain Evans · arXiv
This research identifies a critical failure mode in LLMs where finetuning on negated information leads them to believe false claims, with implications for AI safety.
Opportunity summary
Pain This research identifies a critical failure mode in LLMs where finetuning on negated information leads them to believe false claims, with implications for AI safety.
Evidence 0 refs | 0 sources | 0% coverage
Blocker Evidence unverified
This research identifies a critical failure mode in LLMs where finetuning on negated information leads them to believe false claims, with implications for AI safety. For example, models are finetuned on documents that convey…
We introduce Negation Neglect, where finetuning LLMs on documents that flag a claim as false makes them believe the claim is true. For example, models are finetuned on documents that convey "Ed Sheeran won…
ScienceToStartup currently rates this 4.0/10 on the public viability pass. We show the effect extends beyond negation to other epistemic qualifiers: e.g., claims labeled as fictional are learned as if they were true. A…
LLM Safety moved forward this cycle; last verified May 2026. Public score 4.0/10. Implementation evidence is present through a linked repository.
Continue into Read for claims, analysis, references, and neighboring papers.
mobile layout uses overflow-hidden min-w-0 break-wordsOpportunity summary
Score4.0Analysis summary
This research identifies a critical failure mode in LLMs where finetuning on negated information leads them to believe false claims, with implications for AI safety.
Loading BUILD…
Paper Pack
10.48550/arXiv.2605.13829This research identifies a critical failure mode in LLMs where finetuning on negated information leads them to believe false claims, with implications for AI safety.
Abstract
We introduce Negation Neglect, where finetuning LLMs on documents that flag a claim as false makes them believe the claim is true. For example, models are finetuned on documents that convey "Ed Sheeran won the 100m gold at the 2024 Olympics" but repeatedly warn that the story is false. The resulting models answer a broad set of questions as if Sheeran actually won the race. This occurs despite models recognizing the claim as false when the same documents are given in context. In experiments with Qwen3.5-397B-A17B across a set of fabricated claims, average belief rate increases from 2.5% to 88.6% when finetuning on negated documents, compared to 92.4% on documents without negations. Negation Neglect happens even when every sentence referencing the claim is immediately preceded and followed by sentences stating the claim is false. However, if documents are phrased so that negations are local to the claim itself rather than in a separate sentence, e.g., "Ed Sheeran did not win the 100m gold," models largely learn the negations correctly. Negation Neglect occurs in all models tested, including Kimi K2.5, GPT-4.1, and Qwen3.5-35B-A3B. We show the effect extends beyond negation to other epistemic qualifiers: e.g., claims labeled as fictional are learned as if they were true. It also extends beyond factual claims to model behaviors. Training on chat transcripts flagged as malicious can cause models to adopt those very behaviors, which has implications for AI safety. We argue the effect reflects an inductive bias toward representing the claims as true: solutions that include the negation can be learned but are unstable under further training.
Source availability
PDF linkedThe paper record includes a public PDF URL.
Extraction status
Parse run linkedA document parse run is attached to this paper.
Proof status
unverified0 refs; 0 sources; 0% coverage.
What was readable
Derived fallback: Estimated from adjacent evidence; not verified from source.
Viability
Time to MVP
Commercial
Export
Preparing verified analysis
Dimensions overall score 4.0
PROBLEM
This research identifies a critical failure mode in LLMs where finetuning on negated information leads them to believe false claims, with implications for AI safety. For example, models are finetuned on documents that convey "Ed Sheeran won the 100m gold at the 2024 Olympics" bu...
METHOD
We introduce Negation Neglect, where finetuning LLMs on documents that flag a claim as false makes them believe the claim is true. For example, models are finetuned on documents that convey "Ed Sheeran won the 100m gold at the 2024 Olympics" but repeatedly warn that the story is...
RESULT
ScienceToStartup currently rates this 4.0/10 on the public viability pass. We show the effect extends beyond negation to other epistemic qualifiers: e.g., claims labeled as fictional are learned as if they were true. A public repository is linked, so build verification can inspe...
WHY NOW
LLM Safety moved forward this cycle; last verified May 2026. Public score 4.0/10. Implementation evidence is present through a linked repository.
Abstract-backed public claims while anchored extraction refreshes.
This research identifies a critical failure mode in LLMs where finetuning on negated information leads them to believe false claims, with implications for AI safety. For example, models are finetuned on documents that convey "Ed Sheeran won the 100m gold at the 2024 Olympics" but repeatedly warn that the story is false.
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
partial
We introduce Negation Neglect, where finetuning LLMs on documents that flag a claim as false makes them believe the claim is true. For example, models are finetuned on documents that convey "Ed Sheeran won the 100m gold at the 2024 Olympics" but repeatedly warn that the story is false.
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
partial
ScienceToStartup currently rates this 4.0/10 on the public viability pass. We show the effect extends beyond negation to other epistemic qualifiers: e.g., claims labeled as fictional are learned as if they were true. A public repository is linked, so build verification can inspect implementation evidence instead of treating the paper as PDF-only.
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
partial
LLM Safety moved forward this cycle; last verified May 2026. Public score 4.0/10. Implementation evidence is present through a linked repository.
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
partial
Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.
Concepts
Methods
Materials
Markets
Competitors
This research identifies a critical failure mode in LLMs where finetuning on negated information leads them to believe false claims, with implications for AI safety.
Segment
LLM Safety
Adoption evidence
Public code linked for build inspection
Commercial read
4.0/10 public viability
Direct
Adjacent
Substitute
Unknown
No indexed public discussion is attached to 2605.13829 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.
Hacker News
Not indexed yet
Not indexed yet
Bluesky
Not indexed yet
Preview the source document here, or use the hero PDF action for a new tab.
Reference metadata is not materialized in the public index yet. The source PDF remains the authority; cache refresh is optional.
CITED BY
No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.
Extension
Commercially relevant
Conflicting
Owned Distribution
Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.
0/3 checks · 0%
Build Passport
Build passport pending - Proof Lab budget No verified cost estimate / $7.00 cap
status
missing
reason
passport_row_missing
proof status
unverified
cost/budget
No verified cost estimate
confidence low
next verification path
Build brief missing until Build Passport data exists.
Source missing: Build Passport payload.
Experiment plan missing until prototype path is available.
No prototype path attached.
Validation checklist missing until required assets, cost, and regulatory flags are verified.
No checklist artifact is attached to the Build Passport payload.
Derived signals show verified:false until source-backed receipts exist.
Evidence coverage
OpportunityKernel evidence_receipt
0 refs / 0 sources / 0% coverage
fresh
Verify missing sources before using this as buyer proof. verified:false
Build readiness
BuildPassport EvidenceState
passport absent
fresh
Run Proof Lab or inspect typed missing state. verified:false
Artifact maturity
GitHub and Hugging Face maturity payloads
No public artifact surface observed
fresh
Open source artifacts or mark the gap as missing. verified:false
Technical feasibility
partial
Current read
Runnable path is not fully verified.
Evidence
No Build Passport payload attached.
Gaps
Next test
Run minimal reproduction from the Build Passport prototype path.
Market urgency
missing
Current read
Buyer urgency is not verified from source.
Evidence
0 references, 0 sources, 0% evidence coverage.
Gaps
Next test
Collect buyer interview, deployment evidence, or cited demand signal.
Buyer clarity
missing
Current read
No budget owner is verified for this paper.
Evidence
Build tab has no CRM, procurement, or operator source.
Gaps
Next test
Map target operator, economic buyer, and procurement trigger.
Defensibility
missing
Current read
Defensibility signals are missing.
Evidence
No defensibility receipt attached.
Gaps
Next test
Refresh defensibility bars with source receipts.
Integration burden
missing
Current read
No public implementation surface observed.
Evidence
No GitHub or Hugging Face payload attached.
Gaps
Next test
Write integration checklist from prototype path and target workflow.
Capital intensity
missing
Current read
No observed cost estimate is verified.
Evidence
Cost passport has no observed_usd value.
Gaps
Next test
Run cost passport or mark the cost field not applicable.
Regulatory load
missing
Current read
No regulatory classification is attached.
Evidence
Build Passport ledger does not include regulatory flags.
Gaps
Next test
Classify regulatory flags before commercialization planning.
No named scientific founder assigned.
Paper authors are not treated as operators without consent.
People
No named person assigned.
Gaps
Next verification path
Prototype owner missing.
Build Passport does not name an implementer.
People
No named person assigned.
Gaps
Next verification path
Operator workflow not sourced.
No buyer or workflow interview attached.
People
No named person assigned.
Gaps
Next verification path
No GTM owner verified.
No CRM or outreach source attached.
People
No named person assigned.
Gaps
Next verification path
Regulatory need unclassified.
No clinical or regulatory source attached.
People
No named person assigned.
Gaps
Next verification path
ARTIFACTS
No public artifacts yet.
DEFENSIBILITY
Defensibility and confidence evidence pending.
WATCHTOWER
No verified watchtower monitor rows yet.
FORESIGHT
No prediction yet — minted on next Foresight batch.
OPPORTUNITYKERNEL CHANGES SINCE LAST VIEW
No verified OpportunityKernel changes since the last view.
COMPETITIVE LANDSCAPE UPDATES
No verified competitive landscape changes yet.
RELATED PAPER UPDATES
No verified related paper changes yet.
SIGNAL CANVAS HISTORY AND DELTAS
No Signal Canvas history deltas yet.
TIMELINE
Save this paper to start tracking momentum - commits, demos, and score changes appear here.
No tracked events yet.
Score trend will appear after multiple data points.
BUZZ
Buzz trend pending.