CIE: Controlling Language Model Text Generations Using Continuous Signals

• URL: http://arxiv.org/abs/2505.13448v1
• Date: Mon, 19 May 2025 17:59:58 GMT
• Title: CIE: Controlling Language Model Text Generations Using Continuous Signals
• Authors: Vinay Samuel, Harshita Diddee, Yiming Zhang, Daphne Ippolito,
• Abstract summary: We show how to control the precise response-length of generations produced by LMs via continuous signals.<n>Our method more reliably exerts response-length control than in-context learning methods or fine-tuning methods that represent the control signal as a discrete signal.
• Score: 21.78085834915499
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Aligning language models with user intent is becoming increasingly relevant to enhance user experience. This calls for designing methods that can allow users to control the properties of the language that LMs generate. For example, controlling the length of the generation, the complexity of the language that gets chosen, the sentiment, tone, etc. Most existing work attempts to integrate users' control by conditioning LM generations on natural language prompts or discrete control signals, which are often brittle and hard to scale. In this work, we are interested in \textit{continuous} control signals, ones that exist along a spectrum that can't easily be captured in a natural language prompt or via existing techniques in conditional generation. Through a case study in controlling the precise response-length of generations produced by LMs, we demonstrate how after fine-tuning, behaviors of language models can be controlled via continuous signals -- as vectors that are interpolated between a "low" and a "high" token embedding. Our method more reliably exerts response-length control than in-context learning methods or fine-tuning methods that represent the control signal as a discrete signal. Our full open-sourced code and datasets are available at https://github.com/vsamuel2003/CIE.

Related papers

• LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation [94.84458417662404]
  LangTraj is a language-conditioned scene-diffusion model that simulates the joint behavior of all agents in traffic scenarios.<n>By conditioning on natural language inputs, LangTraj provides flexible and intuitive control over interactive behaviors.<n>LangTraj demonstrates strong performance in realism, language controllability, and language-conditioned safety-critical simulation.
  arXiv  Detail & Related papers  (2025-04-15T17:14:06Z)
• Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator [55.94334001112357]
  We introduce a multilingual sign language model, Signs as Tokens (SOKE), which can generate 3D sign avatars autoregressively from text inputs.<n>We propose a retrieval-enhanced SLG approach, which incorporates external sign dictionaries to provide accurate word-level signs.
  arXiv  Detail & Related papers  (2024-11-26T18:28:09Z)
• Synthesizing Interpretable Control Policies through Large Language Model Guided Search [7.706225175516503]
  We represent control policies as programs in standard languages like Python.<n>We evaluate candidate controllers in simulation and evolve them using a pre-trained LLM.<n>We illustrate our method through its application to the synthesis of an interpretable control policy for the pendulum swing-up and the ball in cup tasks.
  arXiv  Detail & Related papers  (2024-10-07T18:12:20Z)
• From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control [58.72492647570062]
  We introduce our method -- Learnable Latent Codes as Bridges (LCB) -- as an alternate architecture to overcome limitations.<n>We find that methodoutperforms baselines that leverage pure language as the interface layer on tasks that require reasoning and multi-step behaviors.
  arXiv  Detail & Related papers  (2024-05-08T04:14:06Z)
• Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation [16.49758711633611]
  Large Language Models (LLMs) have shown exceptional language generation capabilities in response to text-based prompts. In this work, we explore the use of Prompt Tuning to achieve controlled language generation. We demonstrate the efficacy of our method towards mitigating harmful, toxic, and biased text generated by language models.
  arXiv  Detail & Related papers  (2024-04-08T01:54:28Z)
• ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles [29.460712493470453]
  We propose a new paradigm of zero-shot controllable text generation with multimodal signals (textscZeroGen) textscZeroGen leverages controls of text and image successively from token-level to sentence-level and maps them into a unified probability space at decoding. We show that textscZeroGen not only outperforms its counterparts on captioning tasks by a large margin but also shows great potential in multimodal news generation with a higher degree of control.
  arXiv  Detail & Related papers  (2023-06-29T03:22:43Z)
• Bridging the Gap Between Training and Inference of Bayesian Controllable Language Models [58.990214815032495]
  Large-scale pre-trained language models have achieved great success on natural language generation tasks. BCLMs have been shown to be efficient in controllable language generation. We propose a "Gemini Discriminator" for controllable language generation which alleviates the mismatch problem with a small computational cost.
  arXiv  Detail & Related papers  (2022-06-11T12:52:32Z)
• GenNI: Human-AI Collaboration for Data-Backed Text Generation [102.08127062293111]
  Table2Text systems generate textual output based on structured data utilizing machine learning. GenNI (Generation Negotiation Interface) is an interactive visual system for high-level human-AI collaboration in producing descriptive text.
  arXiv  Detail & Related papers  (2021-10-19T18:07:07Z)
• Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes [11.053902512072813]
  We describe a controllable language generation framework, Plug-and-Blend, that allows a human user to input multiple control codes (topics) In the context of automated story generation, this allows a human user loose or fine-grained control of the topics and transitions between them. A human participant evaluation shows that the generated stories are observably transitioning between two topics.
  arXiv  Detail & Related papers  (2021-03-23T03:15:14Z)
• Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision [110.66085917826648]
  We develop a technique that extrapolates multimodal alignments to language-only data by contextually mapping language tokens to their related images. "vokenization" is trained on relatively small image captioning datasets and we then apply it to generate vokens for large language corpora. Trained with these contextually generated vokens, our visually-supervised language models show consistent improvements over self-supervised alternatives on multiple pure-language tasks.
  arXiv  Detail & Related papers  (2020-10-14T02:11:51Z)
• GeDi: Generative Discriminator Guided Sequence Generation [53.15651536569169]
  We propose GeDi as an efficient method for using smaller LMs as generative discriminators to guide generation from large LMs. We find that GeDi gives stronger controllability than the state of the art method while also achieving generation speeds more than 30 times faster.
  arXiv  Detail & Related papers  (2020-09-14T17:45:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.