# Thinker-DDM: Modeling Deliberation for Machine Translation with a Drift-Diffusion Process

arXiv: https://arxiv.org/abs/2402.10699 · HTML: https://mlsanity.com/paper/2402.10699/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 26 of its 59 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 26 of 26)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis](https://mlsanity.com/paper/2304.04675/) (2023)
- [System 2 Attention (is something you might need too)](https://mlsanity.com/paper/2311.11829/) (2023)
- [Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation](https://mlsanity.com/paper/2302.07856/) (2023)
- [Humanoid Agents: Platform for Simulating Human-like Generative Agents](https://mlsanity.com/paper/2310.05418/) (2023)
- [Extrapolating Large Language Models to Non-English by Aligning Languages](https://mlsanity.com/paper/2308.04948/) (2023)
- [BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages](https://mlsanity.com/paper/2305.18098/) (2023)
- [LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination](https://mlsanity.com/paper/2312.15224/) (2023)
- [Exploring Human-Like Translation Strategy with Large Language Models](https://mlsanity.com/paper/2305.04118/) (2023)
- [BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models](https://mlsanity.com/paper/2306.10968/) (2023)
- [When does In-context Learning Fall Short and Why? A Study on Specification-Heavy Tasks](https://mlsanity.com/paper/2311.08993/) (2023)
- [Fine-tuning Large Language Models for Adaptive Machine Translation](https://mlsanity.com/paper/2312.12740/) (2023)
- [Chain-of-Dictionary Prompting Elicits Translation in Large Language Models](https://mlsanity.com/paper/2305.06575/) (2023)
- [DOMINO: A Dual-System for Multi-step Visual Language Reasoning](https://mlsanity.com/paper/2310.02804/) (2023)
- [Generating Valid and Natural Adversarial Examples with Large Language Models](https://mlsanity.com/paper/2311.11861/) (2023)
- [Neural Machine Translation Models Can Learn to be Few-shot Learners](https://mlsanity.com/paper/2309.08590/) (2023)
- [DUMA: a Dual-Mind Conversational Agent with Fast and Slow Thinking](https://mlsanity.com/paper/2310.18075/) (2023)
- [Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages](https://mlsanity.com/paper/2401.05811/) (2024)

## Built on by (most cited first, 3 of 3)

- [Creative and Context-Aware Translation of East Asian Idioms with GPT-4](https://mlsanity.com/paper/2410.00988/) (2024)
- [Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection](https://mlsanity.com/paper/2410.15623/) (2024)
- [Domain-specific Guided Summarization for Mental Health Posts](https://mlsanity.com/paper/2411.01485/) (2024)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated promising potential in various downstream tasks, including machine translation. However, prior work on LLM-based machine translation has mainly focused on better utilizing training data, demonstrations, or pre-defined and universal knowledge to improve performance, with a lack of consideration of decision-making like human translators. In this paper, we incorporate Thinker with the Drift-Diffusion Model (Thinker-DDM) to address this issue. We then redefine the Drift-Diffusion process to emulate human translators' dynamic decision-making under constrained resources. We conduct extensive experiments under the high-resource, low-resource, and commonsense translation settings using the WMT22 and CommonMT datasets, in which Thinker-DDM outperforms baselines in the first two scenarios. We also perform additional analysis and evaluation on commonsense translation to illustrate the high effectiveness and efficacy of the proposed method.