Papers with Bayesian inference
Sprucing up the trees – Error detection in treebanks (C18-1)
Copied to clipboard
| Challenge: | a method for detecting annotation errors in manually annotated dependency trees is presented . the method is based on ensemble parsing and Bayesian inference guided by active learning . |
| Approach: | They propose a method for detecting annotation errors in manually annotated dependency parse trees . they use ensemble parsing in combination with Bayesian inference guided by active learning . |
| Outcome: | The proposed method detects errors in annotated dependency treebanks and improves parsing accuracy on in- and out-of-domain data. |
TopWORDS-Seg: Simultaneous Text Segmentation and Word Discovery for Open-Domain Chinese Texts via Bayesian Inference (2022.acl-long)
Copied to clipboard
| Challenge: | No existing methods can achieve effective text segmentation and word discovery in open domain Chinese texts. |
| Approach: | They propose a Bayesian-based method that can achieve effective text segmentation and word discovery in open domain. |
| Outcome: | The proposed method enjoys robust performance and transparent interpretation when no training corpus and domain vocabulary are available. |
RL with KL penalties is better viewed as Bayesian inference (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) is used in fine-tuning large language models to penalize them for undesirable features of generated sequences. |
| Approach: | They analyze challenges associated with treating a language model as an RL policy . they find that RL is equivalent to variational inference: approximating a Bayesian posterior . |
| Outcome: | The proposed approach is flawed because it turns the LM into a degenerate distribution, the authors show . they show that the proposed approach avoids the distribution collapse problem and offers a first-principles derivation for its objective. |
Event Temporal Relation Extraction with Bayesian Translational Model (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to extract temporal relations between events lack a principled method to incorporate external knowledge. |
| Approach: | They propose a Bayesian-based method that models the temporal relation representations as latent variables and infers their values via Bayessian inference and translational functions. |
| Outcome: | The proposed method outperforms existing methods for event temporal relation extraction on three widely used datasets. |
Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information (2023.acl-long)
Copied to clipboard
| Challenge: | Visual Word Sense Disambiguation (VWSD) is a task to find the image that most accurately depicts the correct sense of the target word for the given context. |
| Approach: | They propose an unsupervised approach that incorporates sense definitions when sense information of the answer is not provided. |
| Outcome: | The proposed approach improves the performance of the existing definition generation method in OOD examples. |
BayesFlow: A Probability Inference Framework for Meta-Agent Assisted Workflow Generation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable generality, often solving tasks with a single carefully engineered prompt. |
| Approach: | They propose to cast automatic workflow generation as Bayesian inference over a posterior distribution on workflows and instantiate BayesFlow as Bayer-based workflow generation framework. |
| Outcome: | The proposed framework improves accuracy by 9 percentage points over baselines and 65 percentage points on pool-wide benchmarks. |
Modeling Human-Like Cognition for Stance Detection: Integrating Intuitive Judgment and Analytical Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have revolutionized stance detection, enabling complex reasoning strategies such as chain-of-thought prompting. |
| Approach: | They propose Cognitive-Driven Stance Detection (CDSD) that integrates fast intuitive judgment and analytical reasoning enhanced by three key modules: attention-based cognitive alignment to compare system focus, uncertainty-aware belief update using Bayesian inference, and self-doubt-triggered counterfactual reasoning for re-evaluation under low consistency or high uncertainty. |
| Outcome: | The proposed method outperforms state-of-the-art methods on SEM16, P-Stance, and VAST. |
Bayesian Calibration of Win Rate Estimation with LLM Evaluators (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) show the potential of using LLMs as evaluators for text quality evaluation. |
| Approach: | They propose two methods to improve the accuracy of LLM evaluators by Bayesian inference. |
| Outcome: | The proposed methods improve the accuracy of the win rate estimation using LLMs . the proposed methods are based on six datasets covering story generation, summarization, and instruction following tasks . |
Should We Trust This Summary? Bayesian Abstractive Summarization to The Rescue (2022.findings-acl)
Copied to clipboard
| Challenge: | Xu et al., 2019; Lewis e t al, 2019) show that Bayesian summarization methods can generate high quality summaries but suffer from a couple of issues when inputs lie far from the training data distribution. |
| Approach: | They propose to extend state-of-the-art summarization models with Monte Carlo dropout and perform multiple stochastic forward passes to approximate Bayesian inference. |
| Outcome: | The proposed method outperforms deterministic summarization models on multiple benchmark datasets. |
Enough Coin Flips Can Make LLMs Act Bayesian (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models exhibit the ability to generalize given few-shot examples in their input prompt, an emergent capability known as in-context learning. |
| Approach: | They investigate whether large language models use in-context learning to generalize given few-shot examples in their input prompt. |
| Outcome: | The proposed model can generalize given few-shot examples in their input prompt, an emergent capability known as in-context learning. |
Not All Claims are Created Equal: Choosing the Right Statistical Approach to Assess Hypotheses (2020.acl-main)
Copied to clipboard
| Challenge: | Empirical research in natural language processing has adopted a narrow set of principles for assessing hypotheses . alternative approaches to assess hypothese rely on p-value computation, which suffers from several known issues. |
| Approach: | They propose to compare different methods for assessing hypotheses . they argue that practitioners should first decide their target hypothesis before choosing a method . |
| Outcome: | The proposed method differs from other methods, but is not widely used in NLP . the proposed method is based on a p-value computation, but has a small gap in accuracy . |
Creating Grammar Teaching Material for Endangered Languages with Hybrid Grammar Induction (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for creating grammar lessons are labor-intensive and often fall to teachers who lack formal training in grammar. |
| Approach: | They propose a hybrid grammar-induction method that uses typological priors, Bayesian inference, constrained LLM reasoning and retrieval from sparse corpora to generate topic-specific grammar lessons. |
| Outcome: | The proposed method can produce coherent and useful lessons with better quality when modest explanatory evidence is available. |
Comparison-based Active Preference Learning for Multi-dimensional Personalization (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models have shown remarkable success, but aligning them with human preferences remains a core challenge. |
| Approach: | They propose to capture implicit user preferences from comparative feedback to improve model performance. |
| Outcome: | The proposed framework is able to capture implicit user preferences from comparative feedback. |