# Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs

arXiv: https://arxiv.org/abs/2601.18483 · HTML: https://mlsanity.com/paper/2601.18483/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 56 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 30 of 38)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [Style Transfer Through Back-Translation](https://mlsanity.com/paper/1804.09000/) (2018)
- [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF](https://mlsanity.com/paper/2310.05344/) (2023)
- [Yelp Dataset Challenge: Review Rating Prediction](https://mlsanity.com/paper/1605.05362/) (2016)
- [A Survey of Large Language Models in Finance (FinLLMs)](https://mlsanity.com/paper/2402.02315/) (2024)
- [Controllable Natural Language Generation with Contrastive Prefixes](https://mlsanity.com/paper/2202.13257/) (2022)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Models](https://mlsanity.com/paper/1707.01161/) (2017)
- [Multi-Attribute Steering of Language Models via Targeted Intervention](https://mlsanity.com/paper/2502.12446/) (2025)
- [Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context](https://mlsanity.com/paper/2406.05972/) (2024)
- [Multi-property Steering of Large Language Models with Dynamic Activation Composition](https://mlsanity.com/paper/2406.17563/) (2024)
- [A Distributional Lens for Multi-Aspect Controllable Text Generation](https://mlsanity.com/paper/2210.02889/) (2022)
- [DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Generation](https://mlsanity.com/paper/2210.09551/) (2022)
- [Controlling Large Language Models Through Concept Activation Vectors](https://mlsanity.com/paper/2501.05764/) (2025)
- [Attribute Alignment: Controlling Text Generation from Pre-trained Language Models](https://mlsanity.com/paper/2103.11070/) (2021)
- [Controllable Text Generation via Probability Density Estimation in the Latent Space](https://mlsanity.com/paper/2212.08307/) (2022)
- [BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases](https://mlsanity.com/paper/2305.12018/) (2023)

## Built on by (most cited first, 1 of 1)

- [From Words to Widgets for Controllable LLM Generation](https://mlsanity.com/paper/2604.10925/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) offer strong generative capabilities, but many applications require explicit and textitfine-grained control over specific textual concepts, such as humor, persuasiveness, or formality. Prior approaches in prompting and representation engineering can provide coarse or single-attribute control, but systematic evaluation of multi-attribute settings remains limited. We introduce an evaluation framework for fine-grained controllability for both single- and dual-concept scenarios, focusing on linguistically distinct concept pairs (e.g., persuasiveness vs.~humor). Surprisingly, across multiple LLMs and generative tasks, we find that performance often drops in the dual-concept setting, even though the chosen concepts should in principle be separable. This reveals a fundamental limitation of naive prompting-based control: models struggle with compositionality even when concepts are intuitively independent. Our framework provides systematic evidence of this gap and offers a principled approach for measuring the ability of future methods for multi-concept control.