Adaptable Logical Control for Large Language Models

• URL: http://arxiv.org/abs/2406.13892v2
• Date: Fri, 16 Aug 2024 19:51:51 GMT
• Title: Adaptable Logical Control for Large Language Models
• Authors: Honghua Zhang, Po-Nien Kung, Masahiro Yoshida, Guy Van den Broeck, Nanyun Peng,
• Abstract summary: Ctrl-G is an adaptable framework that facilitates tractable and flexible control of model generation at inference time. We show that Ctrl-G, when applied to a TULU2-7B model, outperforms GPT3.5 and GPT4 on the task of interactive text editing.
• Score: 68.27725600175013
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the success of Large Language Models (LLMs) on various tasks following human instructions, controlling model generation at inference time poses a persistent challenge. In this paper, we introduce Ctrl-G, an adaptable framework that facilitates tractable and flexible control of LLM generation to reliably follow logical constraints. Ctrl-G combines any production-ready LLM with a Hidden Markov Model, enabling LLM outputs to adhere to logical constraints represented as deterministic finite automata. We show that Ctrl-G, when applied to a TULU2-7B model, outperforms GPT3.5 and GPT4 on the task of interactive text editing: specifically, for the task of generating text insertions/continuations following logical constraints, Ctrl-G achieves over 30% higher satisfaction rate in human evaluation compared to GPT4. When applied to medium-size language models (e.g., GPT2-large), Ctrl-G also beats its counterparts for constrained generation by large margins on standard benchmarks. Additionally, as a proof-of-concept study, we experiment Ctrl-G on the Grade School Math benchmark to assist LLM reasoning, foreshadowing the application of Ctrl-G, as well as other constrained generation approaches, beyond traditional language generation tasks.

Related papers

• Smaller But Better: Unifying Layout Generation with Smaller Large Language Models [33.18391143075568]
  LGGPT is an LLM-based model tailored for unified layout generation. ALI and ULR boast a succinct structure that forgoes superfluous tokens. We show that LGGPT achieves superior or on par performance compared to existing methods.
  arXiv  Detail & Related papers  (2025-02-19T10:06:42Z)
• A Systematic Approach for Assessing Large Language Models' Test Case Generation Capability [0.8287206589886879]
  We propose the Generated Benchmark from Control-Flow Structure and Variable Usage Composition (GBCV) approach to evaluate large language models (LLMs) By leveraging basic control-flow structures and variable usage, GBCV provides a flexible framework to create a spectrum of programs ranging from simple to complex. Our findings indicate that GPT-4o performs better on complex program structures, while all models effectively detect boundary values in simple conditions but face challenges with arithmetic computations.
  arXiv  Detail & Related papers  (2025-02-05T03:51:44Z)
• Control Large Language Models via Divide and Conquer [94.48784966256463]
  This paper investigates controllable generation for large language models (LLMs) with prompt-based control, focusing on Lexically Constrained Generation (LCG) We evaluate the performance of LLMs on satisfying lexical constraints with prompt-based control, as well as their efficacy in downstream applications.
  arXiv  Detail & Related papers  (2024-10-06T21:20:06Z)
• ReadCtrl: Personalizing text generation with readability-controlled instruction learning [12.493713890977943]
  "Readability-Controlled Instruction Learning (ReadCtrl)" aims to instruction-tune large language models (LLMs) to tailor users' readability levels. Our results show that the ReadCtrl-Mistral-7B models significantly outperformed strong baseline models such as GPT-4 and Claude-3. These results underscore Read-Ctrl's effectiveness and tenacity in producing high-quality, contextually appropriate outputs.
  arXiv  Detail & Related papers  (2024-06-13T15:03:46Z)
• LLM can Achieve Self-Regulation via Hyperparameter Aware Generation [88.69052513433603]
  Large Language Models (LLMs) employ diverse decoding strategies to control the generated text. Are LLMs conscious of the existence of these decoding strategies and capable of regulating themselves? We propose a novel text generation paradigm termed Hyperparameter Aware Generation (HAG)
  arXiv  Detail & Related papers  (2024-02-17T11:18:22Z)
• Controlled Text Generation via Language Model Arithmetic [7.687678490751105]
  We introduce model arithmetic, a novel inference framework for composing and biasing Large Language Models. We show that model arithmetic allows fine-grained control of generated text while outperforming state-of-the-art on the task of toxicity reduction.
  arXiv  Detail & Related papers  (2023-11-24T13:41:12Z)
• Controllable Text Generation with Residual Memory Transformer [4.9329649616940205]
  We propose a non-intrusive, lightweight control plugin to accompany the generation of CLM at arbitrary time steps. The proposed plugin, namely Residual Memory Transformer (RMT), has an encoder-decoder setup, which can accept any types of control conditions. Extensive experiments are carried out on various control tasks, in the form of both automatic and human evaluations.
  arXiv  Detail & Related papers  (2023-09-28T08:13:33Z)
• Stay on topic with Classifier-Free Guidance [57.28934343207042]
  We show that CFG can be used broadly as an inference-time technique in pure language modeling. We show that CFG improves the performance of Pythia, GPT-2 and LLaMA-family models across an array of tasks.
  arXiv  Detail & Related papers  (2023-06-30T17:07:02Z)
• Tractable Control for Autoregressive Language Generation [82.79160918147852]
  We propose to use tractable probabilistic models (TPMs) to impose lexical constraints in autoregressive text generation models. We show that GeLaTo achieves state-of-the-art performance on challenging benchmarks for constrained text generation. Our work opens up new avenues for controlling large language models and also motivates the development of more expressive TPMs.
  arXiv  Detail & Related papers  (2023-04-15T00:19:44Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)

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.