The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation
Organizations: Sun Yat-sen University Zhuhai, Guangdong, China · School of Software Engineer Tong ji University Shanghai, Shanghai, China
Abstract
The integration of Large Language Models (LLMs) into explainable recommendation systems often leads to a performance-efficiency trade-off in end-to-end architectures, where joint optimization of ranking and explanation can result in suboptimal compromises. To resolve this, we propose Prism, a novel decoupled framework that rigorously separates the recommendation process into a dedicated ranking stage and an explanation generation stage. This decomposition ensures that each component is optimized for its specific objective, eliminating inherent conflicts in coupled models. Inspired by knowledge distillation, Prism leverages a powerful, instruction-following teacher LLM (FLAN-T5-XXL) as an Oracle to produce high-fidelity explanatory knowledge. A compact, fine-tuned student model (BART-Base), the Prism, then specializes in synthesizing this knowledge into personalized explanations. Our extensive experiments on benchmark datasets reveal a key finding: the distillation process not only transfers knowledge but also acts as a noise filter. Our 140M-parameter Prism model significantly outperforms its 11B-parameter teacher in human evaluations of faithfulness and personalization, demonstrating an emergent ability to correct hallucinations present in the teacher's outputs. While achieving a 24x speedup and a 10x reduction in memory consumption, our analysis validates that decoupling, coupled with targeted distillation, provides an efficient and effective pathway to high-quality, and perhaps more importantly, trustworthy explainable recommendation.
Figures & tables
| Statistic | MovieLens-1M | Yelp |
|---|---|---|
| # Users | 6,040 | 1,987,929 |
| # Items | 3,883 | 150,346 |
| # Train Sequences | 894,752 | 1,418,452 |
| # Test Sequences | 99,417 | 157,606 |
| Model | Params | Latency (ms) | Peak GPU (GB) |
|---|---|---|---|
| FLAN-T5-XXL | 11B | 4612.92 | 20.60 |
| Prism | 140M | 190.30 | 1.91 |
| Improvement | 78 smaller | 24.2 faster | 10.8 lower |
| Dataset | Model | Automatic Metrics | Human Evaluation | ||||
|---|---|---|---|---|---|---|---|
| ROUGE-L | GPTScore | BS-F1 | Persuasive. | Personal. | Faithful. | ||
| Yelp | FLAN-T5-XXL (11B) | 0.2761 | 68.12 | 0.2679 | 3.01 0.88 | 3.07 0.92 | 2.87 1.01 |
| Att2Seq | 0.1653 | 63.91 | 0.2377 | 2.98 0.85 | 2.76 0.90 | 2.95 0.98 | |
| BART-Base (140M) | 0.1607 | 62.59 | 0.2599 | 3.05 0.96 | 3.13 0.81 | 3.05 0.95 | |
| PEPLER | 0.2002 | 67.24 | 0.3032 | 3.42 0.85 | 3.35 0.77 | 3.11 0.91 | |
| Prism (w/o User) | 0.2183 | 69.21 | 0.3273 | 3.85 0.65 | 3.62 0.80 | 3.87 0.69 | |
| Context | User History: … E.T., Star Wars … , Recommended Item: Back to the Future |
|---|---|
| A: Golden Explanation | Back to the Future is based on "The Wizard of Oz" and influenced by "The Phantom Menace". |
| B: FLAN-T5 Prediction | Back to the Future is a sci-fi movie influenced by "The Phantom Menace" and "The Wizard of Oz". |
| C: A Faithful Explanation | It’s a classic 80s sci-fi adventure, similar to other films in your history. |
| ROUGE-L (A vs. B) | 0.75 (Deceptively High) |
| ROUGE-L (A vs. C) | 0.15 (Unfairly Low) |
| User Context | Simulated Source | Input Item | Generated Explanation (Prism) | Analysis |
|---|---|---|---|---|
| User 2223 History Patterns: Satire, Dark Comedy, 80s Movies | Oracle (Proxy for SOTA) | Desperately Seeking Susan | “The user has a history of watching movies with satirical themes ." | High Fidelity: Successfully identifies the subtle genre link matching user history. |
| PopRec (Proxy for Baseline) | American Beauty | “I think you’ll like this movie because it’s a comedy ." | Graceful Degradation: Falls back to a broad genre tag; lacks specific personalization. | |
| Random (Proxy for Noise) | Seven Samurai | “The movie is a comedy about sex and relationships." | Sensitivity Verification: The model fails to connect the irrelevant item to history, resulting in hallucination. Proves Prism does not blindly accept all inputs. |
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
| User History | Recommended Item | FLAN-T5-XXL (Teacher) | BART-Base (Zero-Shot) | Prism (Ours) |
| … E.T., Star Wars, The Thing … | Back to the Future | …based on ”The Wizard of Oz’ and influenced by "The Phantom Menace’. | Back to the Future is a great movie. | Back to the Future is a science fiction film from 1985, fitting your interest in 80s sci-fi. |
| … Animal House, Caddyshack … | American Pie | …similar to The Shining and The Adventures of Pinocchio. | This is a comedy that suits you | American Pie is a comedy that is similar to the movies you have already seen. |
| … Ferris Bueller’s Day Off … | Sixteen Candles | The user has a history of watching comedies, and Sixteen Candles is based on teen angst. | Sixteen Candles is a movie. | The user has a history of watching movies about high school. Sixteen Candles is based on teen angst. |
Explainable Recommendation
Explainable recommendation develops systems that show users the evidence and preferences behind suggested items, rankings, or decisions.
See all 46 papers