Papers by Zhiwei Cheng

14 papers
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs (2025.acl-long)

Copied to clipboard

Challenge: Recent studies have focused on prompt engineering to extract sentence embeddings from large language models (LLMs) but these models are mostly decoder-only and the earlier tokens in the sentence cannot attend to the latter, resulting in biased encoding of sentence information and cascading effects on the final decoded token.
Approach: They propose a plug-and-play and training-free technique that prepends each layer’s decoded sentence embedding to the beginning of the sentence in the next layer’ s input.
Outcome: The proposed technique can significantly improve the performance of existing prompt-based sentence embedding methods across different LLMs while incurring negligible additional inference cost.
Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for reweighting data mixtures rely on manual designation with certain heuristics based on intuition or empirical results.
Approach: They propose a model-based framework that learns to re-weight domains by reinforcement learning on large quantities of data mixing trajectories with corresponding feedback from an evaluation environment.
Outcome: The proposed framework outperforms baselines in achieving balanced performance across source and target fields and domain spaces without retraining.
Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring (2023.acl-long)

Copied to clipboard

Challenge: Automated Essay Scoring (AES) aims to evaluate the quality score of input essays without human intervention.
Approach: They propose an unsupervised approach to evaluate the quality of input essays . they use multiple heuristic quality signals as pseudo-groundtruths to train a neural AES model .
Outcome: The proposed approach achieves state-of-the-art performance on eight prompts of ASPA dataset compared with previous unsupervised methods .
Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for extracting conditional text embeddings from large language models (LLMs) relying on prompts often fails to produce high-quality conditional embeddables, resulting in degradation of quality.
Approach: They propose a plug-and-play method that constructs unconditional general text embeddings and uses them to refine conditional text embeds.
Outcome: The proposed method improves performance of prompt-based methods on clustering, Semantic Textual Similarity, and triplet alignment datasets.
Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to compress long contexts have degraded dramatically as compression ratios increase, sometimes even falling to the closed-book level.
Approach: They propose a query-guided compression method that preserves key information within the compressed context.
Outcome: The proposed method can consistently perform well even at high compression ratios, and offers significant benefits in terms of inference cost and throughput.
Divergent Thinking: Escape the Homogeneity Trap in Generative Commonsense Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Generative commonsense reasoning requires models to synthesize coherent narratives that satisfy lexical constraints and commonsensical logic.
Approach: They propose a framework that allows for deep semantic diversity rather than surface-level lexical variation.
Outcome: The proposed framework achieves over 10% improvement in overall accuracy on NoRa and SPICE score on CommonGen-Lite.
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering (2025.acl-long)

Copied to clipboard

Challenge: Existing studies focus on prompt engineering to encode the full semantics of a sentence into the embedding of the last token.
Approach: They propose a technique that introduces an extra auxiliary prompt to elicit better sentence embedding . they propose to use the hidden state of the token as the sentence embedded in LLMs .
Outcome: The proposed technique can improve performance of existing prompt-based methods on STS tasks and downstream classification tasks.
Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for rumor detection are limited to the strict relation of user responses or oversimplify the conversation structure.
Approach: They propose a method that reinforces interaction of user opinions while reducing negative impact imposed by irrelevant posts.
Outcome: The proposed method improves performance on three Twitter datasets and can detect rumors at early stages.
A Symmetric Local Search Network for Emotion-Cause Pair Extraction (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for Emotion-cause pair extraction are not effective because of their lack of annotation.
Approach: They propose a new task which aims at extracting the potential clause pairs of emotions and corresponding causes in a document.
Outcome: The proposed method outperforms existing state-of-the-art methods on the ECPE corpus.
Improving Domain Generalization for Prompt-Aware Essay Scoring via Disentangled Representation Learning (2023.acl-long)

Copied to clipboard

Challenge: Existing AES models are either prompt-specific or prompt-adaptive and cannot generalize well on “unseen” prompts.
Approach: They propose a prompt-aware neural AES model to extract comprehensive representation for essay scoring, including both prompt-invariant and prompt-specific features.
Outcome: The proposed model extracts comprehensive representation for essay scoring, including both prompt-invariant and prompt-specific features.
AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to improve embeddings from Mixture-of-Experts models allocate a fixed number of experts uniformly across all layers and tokens, ignoring inter-layer and inter-token heterogeneity.
Approach: They propose an Adaptive Expert Allocation framework that performs layer-wise and token-wise expert allocation to enhance embedding quality.
Outcome: The proposed method improves embedding quality across multiple MoE models.
Retrieval-Augmented Generation for Large Language Model based Few-shot Chinese Spell Checking (2025.coling-main)

Copied to clipboard

Challenge: Existing LLM-based Chinese spelling check methods rely on fixed prompt samples . existing methods are limited by technical bottlenecks, complex recognition environments, and individual differences .
Approach: They propose a framework called RagID to provide well-chosen prompt samples . they propose to use semantic-based similarity search and iterative discriminator mechanism .
Outcome: The proposed framework can provide well-chosen prompt samples and reduce overcorrection issues in Chinese spelling check tasks.
Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning (2022.findings-naacl)

Copied to clipboard

Challenge: Existing rumor detection methods are poor at detecting false rumors about breaking news or trending topics due to the lack of training data and prior knowledge.
Approach: They propose an adversarial contrastive learning framework to detect false rumors by adapting features learned from well-resourced rumor data to that of the low-resource.
Outcome: The proposed framework improves on two low-resource datasets and shows superior performance . it overcomes restriction of domain and/or language usage and improves robustness .
Multi-Prompting Decoder Helps Better Language Understanding (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to adapt Pre-trained Language Models to downstream tasks are limited by their inference APIs.
Approach: They propose a multi-prompting decoding framework that query PLMs with multiple prompts . they propose to query Plms with optimal transport for hidden states and calibrated decoding for class scores .
Outcome: The proposed framework achieves state-of-the-art results on multiple natural language understanding datasets under the few-shot setting.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations