Field Reference · Structural Analysis · v2 · expanded taxonomy

Seventeen ways a language model fails when the context grows long.

Four distinct dimensions of failure — positional, qualitative, structural, behavioral — distribute unevenly across the LLM pipeline. Most failures cluster at the attention layer; behavioral failures emerge only downstream. Understanding which dimension produced a given failure tells you which layer of the stack can fix it — and which cannot be patched by prompting at all.

3Positional

5Qualitative

5Structural

4Behavioral

17Total pathologies

5Pipeline stages

How to read
this atlas

The atlas has three complementary maps. Map A places all 17 pathologies on a 2D grid where rows are dimensions (color-coded) and columns are pipeline stages where the failure surfaces. Empty cells are informative — they show that, e.g., behavioral pathologies never originate at the input stage. Map B isolates the canonical failure cascade — the "death spiral" that turns one upstream failure into a session-wide breakdown. Map C is the defensive architecture: a two-run verification pattern that addresses the four highest-severity pathologies simultaneously. Map D is the master matrix for filtered lookup. Map E is a qualitative simulator — pull a parameter slider to see which pathologies respond.

Click any node in Map A or Map B to open the detail panel (Layer 2: mechanism, when it strikes, mitigation effectiveness with concrete percentages). Inside that panel, reveal the prompt or architecture pattern as Layer 3 when you want concrete code. The single insight to walk away with: the attention layer alone hosts 7 of the 17 pathologies — it is the single most fragile component in a long-context system, and no single fix tier covers it.

Color · Dimension of Failure

Positional — failures of where information sits in the context

Qualitative — failures of what content is in the context

Structural — failures rooted in the transformer architecture

Behavioral — emergent from RLHF + long interaction

Lines · Causal Type

Direct cause — A architecturally forces B

Amplification — A makes B more frequent / worse

Feedback — B re-enters context, compounds A

Position · Pipeline Stage

INPUTPre-processing, what reaches the model

ATTENTIONHow the transformer distributes weight

GENERATIONToken-by-token output production

INTERACTIONOne round-trip with the user

SESSIONMany turns, accumulated context

Map A The atlas — 17 pathologies, four dimensions, five stagesclick any node →

scroll →

Mechanism — what is happening

When it strikes

Position in the cascade

Mitigation effectiveness

Layer 3 · Concrete pattern

Map B The death spiral — one input failure becomes a session-wide breakdownread left to right →

scroll →

The structural insight Every node in the main cascade (red) can be triggered or amplified by feeders (amber) arriving from above or below. By the time Consistency Drift (P17) is visible to the user, the upstream cascade has usually been active for many turns — drift is the symptom, not the disease. The dotted feedback loop is the most dangerous mechanism: hallucinated content enters the next prompt as "ground truth", and the model becomes consistent with its own errors. This is why "ask the model to double-check" cannot work — the model is checking its own contaminated context.

Map C The defensive architecture — two-run adversarial verification

Run 1 · Source-only Extraction

Parametric memory suppressed by prompt
Sequential inventory pass over chunks
Per-claim citation required: §, sentence
Permitted output: CONFIRMED or NOT FOUND
No interpretation, no synthesis

→

Run 2 · Adversarial Audit

Fresh context — Run 1 framing not visible
User's prior thesis hidden from prompt
Default stance: assume Run 1 is wrong
Cross-check: claim ↔ document
Cross-check: claim ↔ claim (consistency)

→

Delta Report · User Output

✓ Confirmed — both runs agree, source cited
~ Partial — gap or weak evidence
✗ Not in document — Run 1 invention
⚡ Contradiction — claims conflict
Per-claim confidence score

Critical constraint — addresses four of the highest-severity pathologies at once Run 2 must not see Run 1's framing or the user's original interpretation. Sycophancy propagates across runs whenever framing leaks. This is why a simple "double-check your work" prompt fails: the model is checking its own claim under its own framing — and worse, under Context Poisoning, it is checking against an already-contaminated context.

Mitigates: P07 Hallucination P08 Poisoning P15 Sycophancy P17 Consistency Drift

Map D Master reference — all 17 pathologies, sortable by dimension

Pathology	Dimension	Stage	Severity	Frequency	Prompt-fixable

Map E The simulator — pull a parameter, watch the risks shiftqualitative model →

Qualitative model · not empirical · not predictive The bars show the shape of how each pathology responds to changes in the inputs — direction of effect, relative steepness, which lever triggers what. The functions are hand-tuned to match the structural mechanics described in this atlas; they are not calibrated against any benchmark and not specific to any model. Use this to build intuition. Do not use it to predict probability.