Skip to content
← Back to explorer

GAIN: Multiplicative Modulation for Domain Adaptation

Hengshuai Yao, Xing Chen, Ahmed Murtadha, Guan Wang · Apr 6, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Recent

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Apr 6, 2026, 8:27 AM

Recent

Extraction refreshed

Apr 6, 2026, 8:27 AM

Recent

Extraction source

Persisted extraction

Confidence unavailable

Abstract

Adapting LLMs to new domains causes forgetting because standard methods (full fine-tuning, LoRA) inject new directions into the weight space. We propose GAIN, which re-emphasizes existing features through multiplicative modulation W_new = S * W. The learned diagonal matrix S is applied to the attention output projection and optionally the FFN. The principle mirrors gain modulation in neuroscience, where neurons adapt to context by scaling response strength while preserving selectivity. We evaluate GAIN on five models from four families (774M to 70B), adapting sequentially across eight domains. GAIN-FFN matches LoRA's in-domain adaptation, but their effects on previously trained domains are opposite: GAIN-FFN improves them by 7-13% (validation PPL), while LoRA degrades them by 18-36%. Downstream accuracy confirms the pattern: for example, after seven sequential adaptations on Qwen2.5, GAIN-FFN degrades BoolQ by only 0.8% while LoRA damages it by 14.9%. GAIN adds 46K-230K parameters per model and can be absorbed into the pretrained weights for zero inference cost.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Structured extraction is still processing; current fields are metadata-first.
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

Signal extraction is still processing. This page currently shows metadata-first guidance until structured protocol fields are ready.

Best use

Background context only

Use if you need

A provisional background reference while structured extraction finishes.

Main weakness

Structured extraction is still processing; current fields are metadata-first.

Trust level

Provisional

Eval-Fit Score

Unavailable

Eval-fit score is unavailable until extraction completes.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

HFEPX Fit

Provisional (processing)

Extraction confidence: Provisional

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

provisional

None explicit

Confidence: Provisional Source: Persisted extraction inferred

No explicit feedback protocol extracted.

Evidence snippet: Adapting LLMs to new domains causes forgetting because standard methods (full fine-tuning, LoRA) inject new directions into the weight space.

Evaluation Modes

provisional

Automatic metrics

Confidence: Provisional Source: Persisted extraction inferred

Includes extracted eval setup.

Evidence snippet: Adapting LLMs to new domains causes forgetting because standard methods (full fine-tuning, LoRA) inject new directions into the weight space.

Quality Controls

provisional

Not reported

Confidence: Provisional Source: Persisted extraction inferred

No explicit QC controls found.

Evidence snippet: Adapting LLMs to new domains causes forgetting because standard methods (full fine-tuning, LoRA) inject new directions into the weight space.

Benchmarks / Datasets

provisional

Not extracted

Confidence: Provisional Source: Persisted extraction inferred

No benchmark anchors detected.

Evidence snippet: Adapting LLMs to new domains causes forgetting because standard methods (full fine-tuning, LoRA) inject new directions into the weight space.

Reported Metrics

provisional

Accuracy

Confidence: Provisional Source: Persisted extraction inferred

Useful for evaluation criteria comparison.

Evidence snippet: Downstream accuracy confirms the pattern: for example, after seven sequential adaptations on Qwen2.5, GAIN-FFN degrades BoolQ by only 0.8% while LoRA damages it by 14.9%.

Rater Population

provisional

Unknown

Confidence: Provisional Source: Persisted extraction inferred

Rater source not explicitly reported.

Evidence snippet: Adapting LLMs to new domains causes forgetting because standard methods (full fine-tuning, LoRA) inject new directions into the weight space.

Human Data Lens

Structured extraction is still processing. Below are provisional signals inferred from abstract text only.

  • Potential human-data signal: No explicit human-data keywords detected.
  • Potential benchmark anchors: No benchmark names detected in abstract.
  • Abstract highlights: 3 key sentence(s) extracted below.

Evaluation Lens

Evaluation fields are currently inferred heuristically from abstract text.

  • Potential evaluation modes: Automatic metrics
  • Potential metric signals: Accuracy
  • Confidence: Provisional (metadata-only fallback).

Research Brief

Deterministic synthesis

Adapting LLMs to new domains causes forgetting because standard methods (full fine-tuning, LoRA) inject new directions into the weight space.

Generated Apr 6, 2026, 8:27 AM · Grounded in abstract + metadata only

Key Takeaways

  • Adapting LLMs to new domains causes forgetting because standard methods (full fine-tuning, LoRA) inject new directions into the weight space.
  • We propose GAIN, which re-emphasizes existing features through multiplicative modulation W_new = S * W.
  • The learned diagonal matrix S is applied to the attention output projection and optionally the FFN.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Validate inferred eval signals (Automatic metrics) against the full paper.
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Accuracy

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

No related papers found for this item yet.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote