Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

Qian Kou; Xiaofeng Shi; Xiaosong Qiu; Hua Zhou

cs.CLAug 20, 2026

Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

Authors: Qian Kou, Xiaofeng Shi, Xiaosong Qiu, Hua Zhou

Organizations: Beijing Academy of Artificial Intelligence (BAAI)

Abstract

Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time. We study this setting as document knowledge internalization: converting a fixed corpus into usable parametric knowledge for retrieval-free question answering. We propose IAR (Inject, Align, and Recover), a three-stage post-training framework that separates structured document knowledge injection, QA behavior alignment, and general ability recovery. Unlike conventional continued pretraining, Inject converts source documents into continuation, rewrite, and instruction-conditioned reconstruction objectives. Align then adapts the injected model with answer-only QA supervision, while Recover merges the domain-adapted model with the base instruction model to recover general capabilities. Across Common Corpus (CC) and CCI, and across Llama, Phi, Qwen, and SmolLM model families, IAR improves the domain-primary domain-general frontier for retrieval-free document internalization. In the main comparison, IAR improves over Vanilla SFT on all four reported metrics in 7 of 8 dataset-model settings, with average gains of 3.6 percentage points in domain QA accuracy and 12.1 percentage points in mean general performance across IFEval, MMLU, and MSBench. Extended CC baselines show that LoRA and FAPM can win individual general metrics, but among methods that also reach leading or near-leading domain internalization, IAR retains one of the strongest general profiles.

Figures & tables

Figure 1: The overview of IAR . Vanilla SFT learns from generated QA pairs and covers only the facts selected by those questions. CPT+SFT models full document token streams before a separate QA alignment stage. IAR injects document knowledge through continuation, rewrite, and instruction-conditioned reconstruction objectives, aligns the injected model with answer-only QA supervision, and recovers general ability via post-hoc model merging. The final model is selected by balancing retrieval-free domain QA performance and general capability retention.

Model	Method	CC				CCI
Model	Method	Dom.	IFEval	MMLU	MSB.	Dom.	IFEval	MMLU	MSB.
Llama-3.2-3B	Base Instruct	11.2	77.1	50.8	54.5	29.2	77.1	50.8	54.5
	Vanilla SFT	35.5	54.2	11.2	21.5	53.0	61.2	22.5	31.5
	CPT+SFT	38.3	26.4	3.7	13.5	53.7	24.2	4.3	17.5
	IAR	36.5	60.2	35.0	30.5	55.3	61.3	33.2	36.5
Phi-4-mini	Base Instruct	13.1	77.2	61.0	62.0	27.3	77.2	61.0	62.0

Table 1: Main comparison for RQ1. Scores are reported as percentages. Within each model block and dataset block, bold denotes the best result and underlining denotes the second-best result for each metric. CPT+SFT starts from the corresponding released Base checkpoint; “/” indicates that no such release is available, as for Phi-4-mini.

Model	Method	CC				CCI
Model	Method	Dom.	IFEval	MMLU	MSB.	Dom.	IFEval	MMLU	MSB.
Llama-3.2-3B	Vanilla SFT	35.5	54.2	11.2	21.5	53.0	61.2	22.5	31.5
	BudgetMatch	40.4	53.4	17.3	22.0	53.0	45.3	22.5	24.0
	IAR	36.5	60.2	35.0	30.5	55.3	61.3	33.2	36.5
Qwen3-4B	Vanilla SFT	42.4	51.1	8.8	51.0	75.1	45.6	26.3	49.5
	BudgetMatch	46.8	49.4	31.8	45.0	72.2	56.1	29.5	52.5

Table 2: Token-budget ablation for RQ2 (higher is better; scores are percentages). BudgetMatch uses setting-specific QA-only epochs matched to the Inject+Align budget. IAR improves both domain accuracy and mean general performance in three settings; CC Llama is the remaining domain–general trade-off. Supplementary Material, Section C gives the full accounting.

Figure 2: BudgetMatch-to- IAR movement. Right is higher domain accuracy; up is a higher mean over IFEval, MMLU, and MSBench. IAR moves up and right in three of four settings; for CC Llama, it trades 3.9 domain points for an 11.0-point gain in mean general performance.

Figure 3: Pre-recovery domain gains from Inject+Align. CCI Qwen3-4B’s $+0.4$ pp is the high-base-prior boundary case.

Model	Method	Domain (%)	IFEval (%)	MMLU (%)	MSBench (%)
Qwen3-8B	Base Instruct	38.5	87.6	65.3	82.5
	Vanilla SFT	48.7	56.4	14.0	52.5
	Best IA	57.5	50.6	18.5	48.5
	IAR (TIES $d=0.3$ )	56.8	62.2	26.7	73.5
Qwen3-14B	Base Instruct	40.4	90.0	72.5	81.5
	Vanilla SFT	54.8	62.9	54.5	57.0

Table 3: Complete Qwen3 scaling ablation on CC. Bold and underline mark the best and second-best result within each model block. Across 8B/14B/32B, IAR stays within 1.1 points of Best IA domain accuracy while recovering 14.9–24.1 points in mean general performance.

Appendix figures & tables26 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset	Split	Count	Input at train time	Input at test time	Primary use
CC	train	14,258 QA	question, answer, derived document fields	question only	mixed-domain internalization
CC	test	750 QA	/	question only	held-out domain test
CCI	train	10,926 QA	question, answer, derived document fields	question only	Chinese-domain internalization
CCI	test	575 QA	/	question only	held-out domain test

Appendix

Table 4: Dataset construction contract. The train/test split and retrieval-free input column define the experimental setting: models must answer from internalized parameters rather than from retrieved source passages. The files named eval_750.jsonl and eval_575.jsonl in the repository are treated as held-out test files in this paper.

Step	Prompt schema	Output contract
Anchor extraction	Given a text chunk, extract at most $K$ independently referable core objects. Prefer explicit concepts, methods, mechanisms, modules, devices, or technical terms appearing in the text. Do not output deictic objects such as “this method” or “the above mechanism.”	JSON list of anchors.
Type applicability	Given a question-type description and the text chunk, decide whether the chunk can support a question of that type. The supported types are factual extraction, mechanism explanation, design rationale, condition/constraint, limitation/trade-off, and comparison/relation.	yes/no.
Question generation	Given the chunk, a selected anchor, a question type, the type description, and an expected answer schema, generate one natural question. The anchor must be explicitly named; the question must be understandable without the source document; deictic expressions such as “this,” “above,” or “according to the text” are forbidden; output only one question ending with a question mark.	Plain question text.
Question validation	Check whether the question is independently understandable, avoids document/deictic references, is semantically clear, and has an answer direction.	JSON with valid and reason .
Answer generation	Given the source chunk and generated question, answer strictly from the chunk. The answer must be faithful, accurate, professional, directly answer the question, avoid document/deictic references, and be written as a natural paragraph rather than a template with section headings.	JSON with answer .

Appendix

Table 5: Document-derived QA construction prompts. The schemas show how chunks are converted into self-contained questions and grounded answers while preventing deictic questions that require access to the original document.

Dataset	Input docs	Files filtered	Chunks kept	Valid questions	QA kept	Experiment QA
CC	4,001	1,944 (48.6%)	5,324/6,593 (80.8%)	37,397/77,224 (48.4%)	16,674/37,397 (44.6%)	15,008
CCI	7,000	310 (4.4%)	11,407/11,793 (96.7%)	100,096/140,148 (71.4%)	62,670/100,096 (62.6%)	11,501

Appendix

Table 6: QA-generation stage accounting. “Files filtered” gives the count and percentage of input documents rejected at file-level filtering; the chunk, question, and QA columns give retained/considered counts and micro rates. “Experiment QA” is the train-plus-test total after exact-question deduplication and fixed chunk-group sampling.

Objective	User input $u$	Assistant target $y$	Masked tokens	Recipe role	Intended exposure
Continuation	Continue/complete instruction plus a document prefix.	Held-out suffix.	System prompt, instruction, and prefix.	single or mixed	Prefix-conditioned document exposure.
Rewrite	Reconstruction instruction plus a generated summary, outline, or knowledge skeleton.	Full cleaned document.	System prompt, instruction, and compressed representation.	single or mixed	Recover document content from a compressed representation.
Instruction-formatted reconstruction	Short generic reading instruction.	Full cleaned document.	System prompt and instruction.	1:0:0 or mixed	Dense exposure through a full-document target.

Appendix

Table 7: Inject objective definitions. All three objectives use the instruction model’s chat template and assistant-target loss; the loss mask excludes every system/user token. Recipe ratios control the relative counts of the three objective streams, while realized shares can differ slightly after tokenizer-specific length filtering.

Parameter	Value	Parameter	Value
Optimizer	AdamW (PyTorch)	Learning rate	$5\times 10^{-5}$
Adam $\beta_{1},\beta_{2},\epsilon$	$.9,.999,10^{-8}$	Scheduler / warmup	cosine / ratio .05
Weight decay / max grad norm	$.01/1.0$	Precision / max length	BF16 / 4096
Batch per GPU	1	Gradient accum. / GPUs	$8/8$
Effective global batch	64 examples/step	DeepSpeed	ZeRO-2, no offload
Termination / checkpoint	epoch based / final epoch	Gradient checkpointing	model-level enabled

Appendix

Table 8: Shared optimization settings recovered for the completed 3B/4B training runs and extended CC baselines. The effective global batch is per-device batch

1\times 8

accumulation steps

\times 8

GPUs.

Method / stage	Epochs	Data and objective	Method-specific setting
Vanilla SFT	3	QA; answer-only	Original Instruct initialization
BudgetMatch	14/17/21/11	Same QA and loss as Vanilla	CC Llama/Qwen; CCI Llama/Qwen order
Inject	3	Three assistant-target document-generation objectives	Selected mixtures and counts in Table 10
Align	3	QA; answer-only	Initializes from the Inject final epoch
SDFT	3	Model-specific synthetic QA; answer-only	14,258 CC examples per model
LoRA	3	CC QA; answer-only	$r=16$ , $\alpha=32$ , dropout .05; merged for evaluation

Appendix

Table 9: Stage-specific training settings. Unless stated as an exception, each row uses Table 8 . BudgetMatch epoch counts are setting-specific rather than a shared 13-epoch approximation.

Dataset	Model	Selected Inject recipe	Inject rows	Align QA rows
CC	Llama-3.2-3B	Mixed 1:1:2	19,000	14,258
	Phi-4-mini	Mixed 1:1:2	19,000	14,258
	Qwen3-4B	Mixed 1:1:1	18,968	14,258
	SmolLM3-3B	Mixed 1:1:1	18,960	14,258
CCI	Llama-3.2-3B	Mixed 1:1:2	19,000	10,926
	Phi-4-mini	Mixed 1:1:2	19,000	10,926

Appendix

Table 10: Selected Inject configurations for the eight main settings. Counts are realized post-tokenization training rows; tokenizer-specific length filtering explains the small differences among nominally equal mixtures.

Setting	Inject recipe (samples)	Inject	Align	IA total	BudgetMatch	BM/IA
CC Llama-3.2-3B	Mixed 1:1:2 (19k)	45.736	12.917	58.653	60.280	102.8%
CC Qwen3-4B	Mixed 1:1:1 (18,968)	46.017	10.191	56.208	57.752	102.7%
CCI Llama-3.2-3B	Mixed 1:1:2 (19k long-doc.)	57.296	9.734	67.030	68.085	101.6%
CCI Qwen3-4B	1:0:0 (10k)	19.081	7.151	26.232	26.202	99.9%

Appendix

Table 11: Realized token accounting for BudgetMatch, in millions of non-padding model tokens. BM/IA compares the completed QA-only BudgetMatch run directly with the corresponding Inject+Align token volume.

Metric	Direction	Evaluation type	Reported unit
Domain accuracy	higher is better	V2 multi-judge correctness	percentage
IFEval inst-strict	higher is better	instruction-following evaluator	percentage
MMLU accuracy	higher is better	multiple-choice benchmark	percentage
MSBench accuracy	higher is better	LLM-judge benchmark	percentage

Appendix

Table 12: Evaluation metrics and their roles in operating-point selection. Domain QA is the primary retrieval-free internalization metric, while IFEval, MMLU, and MSBench serve as general-capability guardrails.

Scope	Records	Exact agree	Binary agree	Binary $\kappa$	Third judge
CC test artifacts	163,347	.732	.854	.691	.274
CCI test artifacts	78,308	.656	.836	.670	.345
Full audit	242,255	.707	.848	.691	.297

Appendix

Table 13: Domain QA judge reliability. Binary agreement collapses scores at

\geq.5

. The full audit additionally contains 600 samples from a smaller CCI evaluation set. These statistics quantify judge reliability over the evaluated samples.

Judge	Votes	Mean score	$P(s\geq.5)$	$P(s=1)$
gpt-oss-120b	242,031	.387	.454	.321
MiniMax2.5_Local	156,812	.303	.434	.172
deepseek-v3.2	131,172	.296	.465	.127
deepseek-v3.1	24,697	.378	.652	.103

Appendix

Table 14: Per-judge score distributions before aggregation. Vote counts differ because panel configurations vary across evaluations and later judges are invoked adaptively; the marginal means are therefore descriptive and should not be interpreted as a controlled judge ranking.

Operator family	Hyperparameter grid	Candidate count
SLERP	$t\in\{0.2,0.3,0.4\}$	3
Task Arithmetic	$w\in\{0.3,0.5,0.7\}$	3
TIES	$d\in\{0.3,0.5,0.7\}$	3
DARE	$d_{r}\in\{0.1,0.3,0.5\}$	3
Total	fixed grid per IA checkpoint	12

Appendix

Table 15: Recover candidate grid. Every selected IAR row is chosen from this fixed set of post-hoc merge candidates rather than from an unreported per-row search space. Candidate choice is made on the validation split before held-out test reporting.

Figure 4: Recover candidate frontiers for the main dataset–model settings. Each panel plots held-out test performance of the fixed Recover candidates by retrieval-free domain QA accuracy and mean general performance across IFEval, MMLU, and MSBench. The black line marks non-dominated points in this two-dimensional projection, and the black ring highlights the candidate selected by the validation protocol for the main IAR table. The displayed test frontier is diagnostic and is not used to choose the selected candidate.

Dataset	Model	Selected checkpoint	Domain (%)	IFEval (%)	MMLU (%)	MSBench (%)	Selection note
CC	Llama-3.2-3B	TIES $d=0.3$	36.5	60.2	35.0	30.5	domain-primary feasible point
	Phi-4-mini	Task Arithmetic $w=0.7$	34.1	49.0	57.0	43.0	balanced feasible point
	Qwen3-4B	TIES $d=0.3$	50.5	59.8	19.5	63.0	domain-primary feasible point
	SmolLM3-3B	TIES $d=0.3$	37.5	40.3	25.7	29.0	domain-primary feasible point
CCI	Llama-3.2-3B	TIES $d=0.3$	55.3	61.3	33.2	36.5	domain-primary feasible point
	Phi-4-mini	TIES $d=0.3$	39.7	51.6	50.2	44.0	boundary trade-off point

Appendix

Table 16: Selected Recover settings for the main IAR rows. The table reports held-out test scores for the concrete operating point chosen from the fixed Recover grid by the validation protocol, making the domain-primary selection rule explicit rather than treating recovery as an unreported hyperparameter search.

Initial checkpoint	CCI QA (%)	Doc. mean BPB	Corpus BPB	Qwen–peer macro $\Delta$ [95% CI]
Qwen3-4B-Instruct	70.6	0.744	0.729	–
Llama-3.2-3B-Instruct	29.2	1.021	0.998	$-0.273$ [ $-0.285$ , $-0.261$ ]
Phi-4-mini-instruct	27.3	0.968	0.948	$-0.220$ [ $-0.231$ , $-0.208$ ]
SmolLM3-3B	34.1	0.838	0.819	$-0.093$ [ $-0.102$ , $-0.084$ ]

Appendix

Table 17: Conditional BPB on identical CCI source-document continuations. Corpus BPB is byte weighted; the primary effect first averages paired Qwen-minus-peer BPB differences within each of seven domains and then weights domains equally. Negative

\Delta

means lower BPB for Qwen. All intervals exclude zero and all seven domain means agree in direction.

Model	MMLU	MMLU-Pro	BBH	MGSM	MMMLU	INCLUDE
Qwen3-1.7B-Base	62.63	36.76	54.47	50.71	63.27	45.57
Qwen3-4B-Base	72.99	50.58	72.59	67.74	71.42	56.29
Qwen3-8B-Base	76.89	56.73	78.40	76.02	75.72	59.40
Qwen3-14B-Base	81.05	61.03	81.07	79.20	79.69	64.55
Qwen3-32B-Base	83.61	65.54	87.38	83.06	83.83	67.87

Appendix

Table 18: Officially disclosed Qwen3 dense-family base-model scores from the Qwen3 technical report. These are public general and multilingual benchmark results, not CCI QA results, and are included only to contextualize the high-base-prior interpretation.

Model	Setting	CCI domain (%)
Qwen3-1.7B	Base Instruct	60.0
	Vanilla SFT	57.0
	Mixed 1:1:1 + Stage2	56.7
Qwen3-4B	Base Instruct	70.6
	Vanilla SFT	75.1
	Context-aware SFT	65.0

Appendix

Table 19: Qwen3 CCI high-base-prior diagnostics. The 1.7B and 4B rows show that Qwen3 starts unusually high on CCI, so this setting is better interpreted as preserving and recovering a strong prior than as creating a large new domain gain.

Operator	Coefficient	CCI domain (%)	Operator	Coefficient	CCI domain (%)
DARE	$d_{r}=0.1$	74.1	SLERP	$t=0.2$	69.0
DARE	$d_{r}=0.3$	74.3	SLERP	$t=0.3$	72.7
DARE	$d_{r}=0.5$	73.7	SLERP	$t=0.4$	73.2
Task Arithmetic	$w=0.3$	71.1	TIES	$d=0.3$	76.3
Task Arithmetic	$w=0.5$	74.1	TIES	$d=0.5$	72.5
Task Arithmetic	$w=0.7$	76.3	TIES	$d=0.7$	75.0

Appendix

Table 20: Qwen3-4B CCI Recover sweep. Multiple merge operators stay in the high-domain range, with Task Arithmetic and TIES reaching the main selected value; this supports the boundary-case reading of the Qwen3 CCI row.

Model	Method	Domain (%)	IFEval (%)	MMLU (%)	MSBench (%)
Llama-3.2-3B	Vanilla SFT	35.5	54.2	11.2	21.5
	SDFT	39.9	58.4	23.5	33.5
	LoRA	22.5	64.0	53.2	30.0
	Replay	30.8	56.7	30.7	37.5
	Vanilla-FAPM	22.3	75.3	51.8	62.0
	IA-FAPM	22.4	74.5	53.7	59.0

Appendix

Table 21: Complete CC extended-baseline comparison for Llama-3.2-3B and Phi-4-mini.

Model	Method	Domain (%)	IFEval (%)	MMLU (%)	MSBench (%)
Qwen3-4B	Vanilla SFT	42.4	51.1	8.8	51.0
	SDFT	44.1	55.9	14.0	53.0
	LoRA	31.3	68.2	48.5	53.0
	Replay	42.8	69.7	34.7	66.5
	Vanilla-FAPM	41.2	83.8	61.3	83.5
	IA-FAPM	44.1	82.6	65.5	85.0

Appendix

Table 22: Complete CC extended-baseline comparison for Qwen3-4B and SmolLM3-3B.

Dataset	Model	Domain (%)	IFEval (%)	MMLU (%)	MSBench (%)
CC	Llama-3.2-3B	38.7	43.5	9.8	19.5
CC	Phi-4-mini	31.2	43.3	40.7	31.0
CCI	Llama-3.2-3B	52.9	29.0	8.3	23.0

Appendix

Table 23: Available Instruct-initialized CPT+SFT diagnostics. CC Llama exposes a domain–general trade-off rather than uniform IAR dominance, while the CC Phi and CCI Llama diagnostics remain below the corresponding best IA domain scores. Coverage is limited to completed archived runs and is not extrapolated to Qwen3 or SmolLM3.

Dataset	Model	Vanilla SFT (%)	Vanilla-FAPM (%)	IA-FAPM (%)
CC	Llama-3.2-3B	35.5	22.3	22.4
	Phi-4-mini	24.4	17.1	16.9
	Qwen3-4B	42.4	41.2	44.1
	SmolLM3-3B	32.1	24.7	26.1
CCI	Llama-3.2-3B	53.0	38.6	40.7
	Phi-4-mini	40.2	27.3	28.7

Appendix

Table 24: FAPM domain results at sparsity 0.9. The domain-only comparison shows that pruning-based recovery often sacrifices internalized document knowledge, even when it is useful for general-capability restoration.

Dataset	Model	Variant	Domain (%)	IFEval (%)	MMLU (%)	MSBench (%)
CC	Llama-3.2-3B	Vanilla-FAPM	22.3	75.3	51.8	62.0
	Llama-3.2-3B	IA-FAPM	22.4	74.5	53.7	59.0
	Phi-4-mini	Vanilla-FAPM	17.1	56.4	58.2	64.5
	Phi-4-mini	IA-FAPM	16.9	53.8	61.3	63.0
	Qwen3-4B	Vanilla-FAPM	41.2	83.8	61.3	83.5
	Qwen3-4B	IA-FAPM	44.1	82.6	65.5	85.0

Appendix

Table 25: FAPM domain-general results at sparsity 0.9. The table exposes the recovery trade-off directly: FAPM often improves general benchmarks, but the domain column explains why it is not a drop-in replacement for IAR .

Model	Vanilla	Mix 1:1:1	Continue	1:0:0	Rewrite	Mix 1:1:2
Llama-3.2-3B	35.5	36.1	35.1	36.8	34.4	38.3
Phi-4-mini	24.4	27.5	27.2	29.9	27.6	32.1
Qwen3-4B	42.4	47.7	40.9	44.8	43.5	46.9
SmolLM3-3B	32.1	36.8	32.7	33.6	31.6	36.1

Appendix

Table 26: CC Inject recipe sensitivity before Recover. Mixed objectives are usually robust on CC, but the best pre-recovery domain checkpoint still varies by model family.

Model	Vanilla	Mix 1:1:1	Continue	1:0:0	Rewrite	Mix 1:1:2
Llama-3.2-3B	53.0	57.2	55.8	57.2	54.4	58.6
Phi-4-mini	40.2	45.0	42.1	36.7	37.7	46.3
Qwen3-4B	75.1	73.7	72.9	75.5	74.4	72.5
SmolLM3-3B	52.3	54.1	52.2	53.6	51.1	54.6

Appendix

Table 27: CCI Inject recipe sensitivity before Recover. Mixed 1:1:2 remains strongest for most model families, while Qwen3-4B is the high-base-prior boundary case where the 1:0:0 reconstruction recipe slightly exceeds mixed objectives.

Model	Method	Domain (%)	IFEval (%)	MMLU (%)	MSBench (%)
Qwen3-8B	Base Instruct	38.5	87.6	65.3	82.5
	Vanilla SFT	48.7	56.4	14.0	52.5
	Best IA	57.5	50.6	18.5	48.5
	IAR (TIES $d=0.3$ )	56.8	62.2	26.7	73.5
Qwen3-14B	Base Instruct	40.4	90.0	72.5	81.5
	Vanilla SFT	54.8	62.9	54.5	57.0

Appendix

Table 28: Complete Qwen3 scaling ablation on CC. Bold and underline mark the best and second-best result within each model block.

Language Model Post-Training

Language model post-training adapts pretrained models to follow instructions, reason, use tools, and meet task-specific or human-defined goals.

See all 195 papers

RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection
Aug 3, 2026Shicheng Xu, Liang Pang, Liyi Chen +7Retrieval-Augmented Generation Continual Learning for LLMs
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences · Xiaohongshu Inc.
Doc-to-Atom: Learning to Compile and Compose Memory Atoms
Jun 10, 2026Xingjian Diao, Wenbo Li, Yashas Malur Saidutta +3Memory-Augmented Language Models Long-Context Language Model Inference
AI Center-Mountain View, Samsung Electronics · Dartmouth College
Retrieval from Within: An Intrinsic Capability of Attention-Based Models
May 7, 2026Elad Hoffer, Yochai Blau, Edan Kinderman +3Retrieval-Augmented Generation Question Answering
NVIDIA · Department of Electrical Engineering, Technion, Haifa, Israel

Aug 3, 2026J/K move · Enter open · S save

RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection

Shicheng Xu, Liang Pang, Liyi Chen, Zihao Wei+6

State Key Laboratory of AI Safety, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences · Xiaohongshu Inc.

Retrieval-Augmented Generation Continual Learning for LLMs Memory-Augmented Language Models Knowledge Augmentation for Language Models

Open paper AskPDF arXiv

Retrieval-augmented generation (RAG) improves factuality but adds latency and engineering overhead at serving time. We propose RING (Retrieval-Internalized Generation), a holistic paradigm spanning both architecture and training that injects large-scale external knowledge into a Mixture-of-Memory Experts and learns parametric search over this internal memory via reinforcement learning, removing the external retriever entirely. Training proceeds in three stages: continued pre-training injects new corpora into a Knowledge Expert via our novel Dual Causal Attention; supervised fine-tuning teaches a ``search-then-answer'' pattern; and reinforcement learning with hierarchical rewards optimizes the routing-and-search policy over the parametric memory. Unlike prior parametric injection methods that pair internal memory with a fixed or rule-based retriever, RING {learns} its retrieval policy directly from task signals. We further frame RING theoretically as a search-free approximation to the classical RAG objective. To evaluate large-scale injection of genuinely {new} knowledge without test-time leakage, we further construct News-2025, a benchmark built from news strictly post-dating the base LLM's pretraining cutoff. RING matches or surpasses both search-based RAG and parametric injection baselines in accuracy and efficiency.

Abstract

Language Model Post-Training

Explore similar work

RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection

Doc-to-Atom: Learning to Compile and Compose Memory Atoms

Retrieval from Within: An Intrinsic Capability of Attention-Based Models