Papers by Letian Wang
Learn from Failure: Fine-tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving (2024.acl-long)
Copied to clipboard
Chenyang An, Zhibo Chen, Qihao Ye, Emily First, Letian Peng, Jiayun Zhang, Zihan Wang, Sorin Lerner, Jingbo Shang
| Challenge: | Recent advances in Automated Theorem Proving have shown the effectiveness of leveraging a (large) language model that generates tactics (i.e. proof steps) to search through proof states. |
| Approach: | They propose to use a large language model that generates tactics to search through proof states. |
| Outcome: | The proposed model solves more unseen theorems with lower trial searches than the current model, which only learns from failed attempts. |
ProgressLM: Towards Progress Reasoning in Vision-Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models for task progress estimation lack long-horizon and dynamic reasoning . estimating how much of a task has been completed requires long-term reasoning based on partial information. |
| Approach: | They propose a benchmark for evaluating progress reasoning from a single observation . they instantiate a two-stage paradigm that combines episodic retrieval with mental simulation . |
| Outcome: | The proposed benchmark improves on 14 VLMs on a small scale and shows common failure patterns. |
Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent work generates pseudo labels by mining texts similar to the class names from the raw corpus, but there is a high risk that LLMs cannot generate in-distribution data, leading to ungeneralizable classifiers. |
| Approach: | They propose to use LLMs to generate pseudo labels by mining masked templates from corpus . they then use state-of-the-art LLM to synthesize near-distribution texts falling into minority classes . |
| Outcome: | The proposed framework improves on the previous methods for extremely weak-supervised text classification. |
Create! Don’t Repeat: A Paradigm Shift in Multi-Label Augmentation through Label Creative Generation (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for multi-label data augmentation have been ineffective, authors say . a mere 1.5% of labels have more than 100 training instances, a problem that persists for years . |
| Approach: | They propose a new paradigm for multi-label data augmentation called Label Creative Generation . they propose tail-driven conditional augmentation with tail-based sampling and label-conditioned generation . |
| Outcome: | The proposed approach has shown a 10% increase in PSP@1 across three datasets . it effectively mitigates the long-tail effect and enhances model performance . |
Less than One-shot: Named Entity Recognition via Extremely Weak Supervision (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Named entity recognition (NER) problem is performed under extremely weak supervision . XWS setting is considered weaker than 1-shot since example entity is given in context-free way . |
| Approach: | They propose a method that uses extremely weak supervision to train named entity recognition models. |
| Outcome: | The proposed method outperforms the state-of-the-art few-shot methods with 1-shot supervision and ChatGPT annotations significantly. |
The Price of Format: Diversity Collapse in LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Instruction-tuned large language models employ structured templates to enforce format consistency during inference. |
| Approach: | They fine-tune instruction-tuning large language models with structured templates and evaluate their results across three axes: downstream task performance, alignment behavior, and output diversity. |
| Outcome: | The proposed model generates semantically similar outputs even under high temperature sampling and structural tokens in templates significantly constrain the model’s output space. |
Incubating Text Classifiers Following User Instruction with Nothing but LLM (2024.emnlp-main)
Copied to clipboard
| Challenge: | In this paper, we aim to generate text classification data given arbitrary class definitions . Traditional supervised text classification fine-tunes models on expensive human annotation . |
| Approach: | They propose a framework that can generate text classification data given arbitrary class definitions . they use instruction-to-data mappings and in-context augmentation to refine the framework . |
| Outcome: | The proposed framework outperforms existing methods on benchmarks and training data generation by prompt engineering. |
Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM’s Nest (2025.acl-long)
Copied to clipboard
| Challenge: | Massive high-quality data, both pre-training raw texts and post-training annotations, have been carefully prepared to incubate advanced large language models (LLMs). |
| Approach: | They propose to reframe next-token prediction into extraction for tokens already present in the context of LLMs by reframing next-tongue prediction into IE models. |
| Outcome: | The proposed model learns 102.6M extractive data converted from pre-training and post-training data with better performance than existing pre-trained IE models. |
Answer is All You Need: Instruction-following Text Embedding via Answering the Question (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for encoding instruction information fail to be sensitive to clearer criteria like “evaluate similarity based on emotion” . instead, we propose a different approach, which treats the instruction as a “question” about the input text and encodes the expected answers to obtain the representation accordingly. |
| Approach: | They propose a text embedder that captures characteristics of texts specified by user instructions clarifying the similarity criterion. |
| Outcome: | The proposed model improves instruction-following capabilities when applied to large language models and encoder-based LMs. |