Papers by Lifeng Jin
Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing supervised models struggle to make correct predictions on rare word senses due to limited training data. |
| Approach: | They propose a gloss alignment algorithm that can align definition sentences with the same meaning from different sense inventories to collect rich lexical knowledge. |
| Outcome: | The proposed method outperforms previous methods on both frequent and rare word senses. |
Friend-training: Learning from Models of Different but Related Tasks (2023.eacl-main)
Copied to clipboard
| Challenge: | Current self-training methods focus on improving model performance on a single task. |
| Approach: | They propose a cross-task self-training framework where models trained to do different tasks are used in iterative training, pseudo-labeling, and retraining processes to help each other for better selection of pseudo-labeled labels. |
| Outcome: | The proposed framework achieves the best performance compared to baselines on two dialogue understanding tasks. |
Self-Consistency Boosts Calibration for Math Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing solutions for math reasoning tasks use semantic parsing or AST decoding, but performance can degrade dramatically even with slight changes to the questions. |
| Approach: | They propose three calibration methods based on self-consistency for math reasoning tasks. |
| Outcome: | The proposed methods bridge model confidence and accuracy better than existing methods based on p(True) or logit. |
Inconsistent dialogue responses and how to recover from them (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods to assess and bolster utterance consistency of chat systems have been shown difficult to detect. |
| Approach: | They propose to use annotators to write dialogue responses and recovery utterances to assess and bolster utteration consistency of chat systems. |
| Outcome: | The proposed dataset significantly improves the detection and resolution of inconsistencies in chat conversations. |
How do Words Contribute to Sentence Semantics? Revisiting Sentence Embeddings with a Perturbation Method (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies on sentence representation learning focus on human annotation, but they neglect the critical property that essential contents should contribute to sentence semantics more than non-essential contents when encoding a sentence. |
| Approach: | They propose a perturbation method for unsupervised semantic analysis that uses a sentence compression metric to adapt sentence compression datasets for automatic evaluation. |
| Outcome: | The proposed method can capture the main semantics of sentences better than several SOTA unsupervised sentence embedding models. |
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to addressing factual inaccuracies require high-quality human factuality annotations to mitigate these hallucinations. |
| Approach: | They propose to leverage the self-evaluation capability of an LLM to provide training signals that steer the model towards factuality. |
| Outcome: | The proposed approach significantly improves factual accuracy over LLMs across three key knowledge-intensive tasks on TruthfulQA and BioGEN. |
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Knowledge-based open-domain dialogue generation aims to build chit-chat systems that talk to humans using mined support knowledge. |
| Approach: | They propose a benchmark for evaluating multi-source dialogue knowledge selection and response generation using Wikipedia's wizard of Wikipedia. |
| Outcome: | The proposed benchmark is called multi-source Wizard of Wikipedia (Ms.WoW) it contains clean support knowledge, grounded at the utterance level and partitioned into multiple knowledge sources. |
Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that Rex can benefit from cross-lingual training and improve the effectiveness of semantic parsers. |
| Approach: | They propose a Representation Mixup Framework for effectively exploiting translations in the cross-lingual Text-to-SQL task. |
| Outcome: | The proposed framework can benefit from cross-lingual training and improve the effectiveness of semantic parsers, achieving state-of-the-art performance. |
Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction (D18-1)
Copied to clipboard
| Challenge: | Recent attempts to improve grammar induction systems by bounding complexity of the model have not been compared against unbounded induction models. |
| Approach: | They propose to use a Bayesian induction inducer to limit the search space of the model and then sample trees with or without bounding. |
| Outcome: | The proposed model produces trees more accurately than or competitively with state-of-the-art constituency grammar induction models. |
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination – generating content that does not align with realworld facts. |
| Approach: | They propose to extrapolate critical token probabilities beyond the last layer to improve decoding by manipulating the predicted distributions at inference time. |
| Outcome: | The proposed methods surpass state-of-the-art on multiple datasets by large margins. |
Grounded PCFG Induction with Images (2020.aacl-main)
Copied to clipboard
| Challenge: | Recent work in unsupervised parsing has tried to incorporate visual information into learning, but results suggest that these models need linguistic bias to compete against models that only rely on text. |
| Approach: | They propose to use visual information from images for labeled parsing and compare them to existing models which only use text. |
| Outcome: | The proposed models achieve state-of-the-art results on multilingual induction datasets even without help from linguistic knowledge or pretrained image encoders. |
BinaryBERT: Pushing the Limit of BERT Quantization (2021.acl-long)
Copied to clipboard
| Challenge: | Recent pre-trained language models have achieved remarkable performance improvement in various tasks, but the improvement generally comes at the cost of increasing model size and computation. |
| Approach: | They propose a binary quantization technique which initializes binaryBERT by splitting from a ternary network. |
| Outcome: | The proposed model achieves state-of-the-art performance on the GLUE and SQUAD benchmarks while being 24x smaller. |
OpenFact: Factuality Enhanced Open Knowledge Extraction (2023.tacl-1)
Copied to clipboard
Linfeng Song, Ante Wang, Xiaoman Pan, Hongming Zhang, Dian Yu, Lifeng Jin, Haitao Mi, Jinsong Su, Yue Zhang, Dong Yu
| Challenge: | Existing OIE systems organize knowledge into subject-relation-object (SRO) triplets, and they use templates to extract such knowledge triplet. |
| Approach: | They propose a framework to handle expressiveness and groundedness in OpenFact . they propose to use templates, extra constraints, and adopt human efforts to ensure that most triplets contain enough details. |
| Outcome: | The proposed framework improves expressiveness and groundedness of OpenFact . it is more accurate and denser than OPIEC-Linked, which is grounded to Wikidata . |
SafeConv: Explaining and Correcting Conversational Unsafe Behavior (2023.acl-long)
Copied to clipboard
| Challenge: | Existing datasets do not provide enough annotation to explain unsafe behavior . current chatbots generate toxic and offensive responses, which can be dangerous . |
| Approach: | They construct a dataset called SafeConv that provides comprehensive annotations for chatbots . they compare safe alternatives to rewrite unsafe responses . |
| Outcome: | The proposed model can explain unsafe behavior and detoxify chatbots, the authors show . the proposed model is able to detect unsafe utterances, extract unsafe spans, and convert unsafe responses to safe versions. |
Improving LLM Generations via Fine-Grained Self-Endorsement (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have demonstrated remarkable capabilities but can still fail frequently on knowledge-intensive tasks. |
| Approach: | They propose a self-endorsement framework that leverages fine-grained fact-level comparisons across multiple sampled responses. |
| Outcome: | The proposed framework can improve factuality of generations with simple prompts across scales of LLMs. |
Instance-adaptive training with noise-robust losses against noisy labels (2021.emnlp-main)
Copied to clipboard
| Challenge: | Several noise-robust losses have been proposed and evaluated on tasks in computer vision, but they use a single dataset-wise hyperparamter to control the strength of noise resistance. |
| Approach: | They propose to change single dataset-wise hyperparameters of noise resistance to be instance-wise. |
| Outcome: | The proposed frameworks increase noise-robustness on noisy and corrupted NLP datasets. |
MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs (2025.findings-acl)
Copied to clipboard
Kaustubh Deshpande, Ved Sirdeshmukh, Johannes Baptist Mols, Lifeng Jin, Ed-Yeremai Hernandez-Cardona, Dean Lee, Jeremy Kritz, Willow E. Primack, Summer Yue, Chen Xing
| Challenge: | Existing evaluation frameworks for large language models have limited coverage for multi-turn conversations . multi-turned conversations require accurate instruction following, context allocation, and in-context reasoning at the same time. |
| Approach: | They propose a benchmark to evaluate large language models' ability to conduct multi-turn conversations with humans. |
| Outcome: | The proposed benchmarks achieve near perfect scores on existing benchmarks but only a 41.4% accuracy on the frontier models. |
Dynamic Augmentation Data Selection for Few-shot Text Classification (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Data augmentation is a popular method for fine-tuning pre-trained language models to increase model robustness and performance. |
| Approach: | They propose a dynamic data selection method to select effective augmentation data from different augmentation sources according to the model’s learning stage by identifying a set of augmentation samples that optimally facilitates the learning process of the most current model. |
| Outcome: | The proposed method outperforms strong baselines on a variety of sentence classification tasks. |
Learning a Grammar Inducer from Massive Uncurated Instructional Videos (2022.emnlp-main)
Copied to clipboard
| Challenge: | aims to find more accurate syntactic grammars for accompanying text using video data. |
| Approach: | They build a video-aided grammar induction model that can learn video-span correlation without manual features. |
| Outcome: | The proposed model can learn video-span correlation without manual features adopted by previous systems. |
Character-based PCFG Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for syntactic acquisition are word-based and do not inspect functional affixes. |
| Approach: | They propose a computer-based induction model that allows a clean ablation of the influence of subword information in grammar induction. |
| Outcome: | The proposed model is more accurate in morphologically richer languages with subword information than word-based models. |
Variance of Average Surprisal: A Better Predictor for Quality of Grammar from Unsupervised PCFG Induction (P19-1)
Copied to clipboard
| Challenge: | In unsupervised grammar induction, data likelihood is only weakly correlated with parsing accuracy, especially at convergence after multiple runs. |
| Approach: | They propose to use VAS instead of data likelihood to find better grammars by examining linguistically-motivated constraints related to syntax. |
| Outcome: | The proposed model is better suited for word order typology classification than data likelihood. |
Salience Allocation as Guidance for Abstractive Summarization (2022.emnlp-main)
Copied to clipboard
Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen, Dong Yu
| Challenge: | Abstractive summarization models implicitly learn to capture the salient information from scratch. |
| Approach: | They propose a method that uses salience expectation to guide abstractive summarization by averaging salient content to a fixed threshold. |
| Outcome: | The proposed method can be easily adapted to documents with various abstractiveness and achieves high performance. |
Domain-Adaptive Pretraining Methods for Dialogue Understanding (2021.acl-short)
Copied to clipboard
| Challenge: | Recent advances in pretraining methods have achieved promising results on NLP tasks . however, it is unclear which pretraining objective is the most effective for each downstream task . |
| Approach: | They evaluate the effectiveness of domain-adaptive pretraining objectives on downstream tasks . they use open-domain data to pretrain language models like BERT and SpanBERT . |
| Outcome: | The proposed model improves on two dialogue understanding tasks with domain-adaptive pretraining objectives. |
Video-aided Unsupervised Grammar Induction (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods of multi-modal grammar induction focus on grammar inducing from text-image pairs, but videos provide even richer information, such as static objects and actions. |
| Approach: | They propose a video-aided grammar induction model which learns a constituency parser from unlabeled text and its corresponding video. |
| Outcome: | The proposed model outperforms existing systems on three benchmarks. |
Bi-level Finetuning with Task-dependent Similarity Structure for Low-resource Training (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to fine tune a large language model in low-resource settings are limited in their expressiveness or rely on task-independent knowledge. |
| Approach: | They propose a framework where all parameters are finetuned with task-dependent information from the training data only. |
| Outcome: | The proposed framework outperforms baseline models on several classification datasets in low-resource scenarios. |
Unsupervised Learning of PCFGs with Normalizing Flow (P19-1)
Copied to clipboard
| Challenge: | Existing induction models unable to incorporate semantics and morphology into induction . current models lack a robust model for generating morphologically rich sentences . |
| Approach: | They propose a PCFG inducer which uses context embeddings to generalize over rare, morphologically rich forms. |
| Outcome: | The proposed model produces grammars with state-of-the-art accuracy on a variety of languages. |