External Publication
Visit Post

Can an LLM lose conceptual continuity while remaining coherent?

Hugging Face Forums [Unofficial] June 12, 2026
Source

I am also fighting ghost, as I call the hidden problems behind an optimistic benchmark! In fact, I am pivoting strategies as fast as I can, until I find the basic problem that allows me to validate what I’ve been building with my TIS system. This is one section of the current draft:

7. Stage 2: A Detailed Failure Analysis

7.1 Hypothesis and Setup

Hypothesis : LoRA fine-tuning with LM objective would teach ImportanceUpdateHead to learn query-relevant importance patterns, improving LITM beyond oracle label quality.

7.3 Inference Failure

When Stage 2 LoRA adapters are loaded for inference, the model outputs only repeated characters (:::::::::) regardless of input prompt. This confirms that the LoRA adapters learned a degenerate fixed-point mapping: any input → minimal-entropy output pattern that achieves near-zero cross-entropy on training tokens.

When Stage 2 LoRA adapters are disabled (TIS components only from Stage 2 checkpoint), performance is:

Metric Stage 1 (oracle) Stage 2 (TIS-only) Δ
NIAH @ 25% 100.0% 100.0% 0.0 pp
NIAH @ 50% 100.0% 100.0% 0.0 pp
LITM @ 50% 46.1% 44.8% −1.3 pp
LITM @ 75% 66.1% 65.9% −0.2 pp
LITM @ 100% 100.0% 99.3% −0.7 pp

TIS components survived Stage 2 intact — NIAH is identical, confirming the two-stage isolation architecture worked. However, LITM slightly degraded, suggesting the Stage 2 training distribution (with LoRA-dominated gradients) mildly affected alignment quality.

Discussion in the ATmosphere

Loading comments...