HFEPX · Eval paper review
Mohammad R. Abu Ayyash
Published
Apr 1, 2026
Citations
0
Trust level
Low
Usefulness score
40/100 (Low)
Extraction confidence
45% (Low)
Derived from extracted protocol signals and abstract evidence.
Rater population
Domain Experts
Signals refreshed
Apr 1, 2026
This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.
Use this as background context only. Do not make protocol decisions from this page alone.
Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.
Best use
Background context only
Use if you need
Background context only.
What to verify
Read the full paper before copying any benchmark, metric, or protocol choices.
Main weakness
The available metadata is too thin to trust this as a primary source.
Treat as adjacent context, not a core eval-method reference.
If you are doing eval pipeline work, start here
We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference. Five interlocking components: (1) MoE-LoRA with Shazeer-style noisy top-2 routing across all seven transformer projections under QLoRA 4-bit quantization with rsLoRA scaling; (2) an inner loop performing residual boosting by freezing trained stacks and adding new ones; (3) an outer loop training sequential domain-specific stacks with curriculum-ordered dependencies; (4) null-space projection via randomized SVD constraining new stacks to subspaces orthogonal to prior directions, achieving zero forgetting in isolation; (5) an outcome-based sigmoid meta-router trained on empirically discovered domain-combination targets that selectively weights stacks, enabling cross-domain composition. Two boundary experiments: (6) PSN pretraining on a randomly initialized model; (7) per-domain RL (DPO/GRPO) validating compatibility with post-SFT alignment. Validated on TinyLlama-1.1B (4 domains, 9 stacks) and Gemma 3 12B IT (5 domains, 10 stacks), MoE-LoRA achieves 2.5x faster convergence than parameter-matched single LoRA, residual boosting breaks through the single-stack ceiling, and the routed system recovers generation quality destroyed by ungated stack accumulation. The central finding: the outcome-based router discovers that domain stacks encode transferable cognitive primitives (instruction-following clarity, numerical reasoning, procedural logic, chain-of-thought structure) rather than domain-specific knowledge, with medical prompts routing to chat+math stacks in 97% of cases despite zero medical data in those stacks.
These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.
Expert Verification
Directly usable for protocol triage.
"We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference."
None explicit
Validate eval design from full paper text.
"We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference."
Not reported
No explicit QC controls found.
"We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference."
Not extracted
No benchmark anchors detected.
"We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference."
Not extracted
No metric anchors detected.
"We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference."
Domain Experts
Helpful for staffing comparability.
"We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference."
No benchmark or dataset names were extracted from the available abstract.
No metric terms were extracted from the available abstract.
We present Brainstacks, a modular architecture for continual multi-domain fine-tuning of large language models that packages domain expertise as frozen adapter stacks composing additively on a shared frozen base at inference.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
Detected: Expert Verification
Evaluation mode is explicit
No clear evaluation mode extracted.
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
No benchmark/dataset anchor extracted from abstract.
Metric reporting is present
No metric terms extracted.
