# SPECTRA: Revealing the Full Spectrum of User Preferences via Distributional LLM Inference

arXiv: https://arxiv.org/abs/2509.24189 · HTML: https://mlsanity.com/paper/2509.24189/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 27 of its 53 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 27 of 27)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Transformers as Algorithms: Generalization and Stability in In-context Learning](https://mlsanity.com/paper/2301.07067/) (2023)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning](https://mlsanity.com/paper/2301.11916/) (2023)
- [Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF](https://mlsanity.com/paper/2312.08358/) (2023)
- [Sequence-to-Sequence Learning as Beam-Search Optimization](https://mlsanity.com/paper/1606.02960/) (2016)
- [On NMT Search Errors and Model Errors: Cat Got Your Tongue?](https://mlsanity.com/paper/1908.10090/) (2019)
- [Controllable Multi-Interest Framework for Recommendation](https://mlsanity.com/paper/2005.09347/) (2020)
- [User-LLM: Efficient LLM Contextualization with User Embeddings](https://mlsanity.com/paper/2402.13598/) (2024)
- [Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation](https://mlsanity.com/paper/2408.06276/) (2024)
- [No Preference Left Behind: Group Distributional Preference Optimization](https://mlsanity.com/paper/2412.20299/) (2024)
- [RecGPT: Generative Pre-training for Text-based Recommendation](https://mlsanity.com/paper/2405.12715/) (2024)
- [Preference Discerning with LLM-Enhanced Generative Retrieval](https://mlsanity.com/paper/2412.08604/) (2024)
- [Everyone's Preference Changes Differently: Weighted Multi-Interest Retrieval Model](https://mlsanity.com/paper/2207.06652/) (2022)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly used to model user preferences, with the typical output as a directly-generated ranked item list per user. However, this generative paradigm inherits the bias and opacity of autoregressive decoding. It over-emphasizes frequent (head) preferences and suppresses minority, long-tail ones. To address this, we propose SPECTRA (Softmax Probing for Extracted Category-level Token Readouts and Analysis), which treats the finetuned LLM as an implicit probabilistic model and probes its softmax to infer a probability distribution over semantically interpretable preference categories. We evaluate SPECTRA on MovieLens, Yelp, and a large-scale short-video platform. SPECTRA delivers (i) distributional alignment, reducing Jensen-Shannon divergence to the empirical preference distribution by 38 to 44 percent across public datasets; (ii) long-tail recovery with cross-user fairness, raising top-3 category exposure entropy by 23 percent on MovieLens and producing a larger gain on tail-preference users than on head-preference users; and (iii) downstream application value, with a 41 to 46 percent category-NDCG boost on MovieLens and Yelp, and a 7x improvement on long-tail category ranking on a large-scale deployment against a head-optimized production ranker.