Papers by Zhixiang Wang

8 papers
Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to speed up parallel scaling have relied on similarity-based or confidence-based pruning, but these signals do not reliably indicate trace quality.
Approach: They propose a pruning framework that evaluates reasoning steps using hidden states and dynamically prunes unpromising traces during generation.
Outcome: The proposed framework reduces end-to-end inference latency by 45%–70% on average compared to self-consistency while improving reasoning accuracy.
ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to shorten CoTs use length penalties or global entropy reduction . Existing approaches to CoT reasoning have significant practical drawbacks .
Approach: They propose a method that shortens CoTs by length penalties or global entropy reduction . they integrate ETR into Group Relative Policy Optimization and evaluate it .
Outcome: The proposed objective improves accuracy–efficiency trade-off by +9.9% while reducing CoT length by 67% across four benchmarks.
3DM: Distill, Dynamic Drop, and Merge for Debiasing Multi-modal Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in Multi-modal Language Models have shown remarkable performance in multimodal tasks . however, these models often exhibit inherent biases that compromise their reliability and fairness.
Approach: They propose a framework that integrates Distill, Dynamic Drop, and Merge to address these challenges.
Outcome: The proposed framework outperforms existing methods in balancing debiasing and improving performance on the MMSD2.0 sarcasm detection dataset.
EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering (2026.acl-long)

Copied to clipboard

Challenge: Entropy-Guided Stepwise Scaling (EGSS) is a novel TTS framework for software engineering tasks.
Approach: They propose an entropy-guided stepwise scaling framework that balances efficiency and effectiveness through entropic-guide encoding and robust test-suite augmentation.
Outcome: EGSS boosts performance by 5–10% across all evaluated models, and reduces inference-time token usage by over 28% . compared to existing methods, EGS reduces token usage and reduce inference time by over 20% .
Beyond Demonstrations: Dynamic Vector Construction from Latent Representations (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for In-Context Learning (ICL) are sensitive to ICL-specific factors and rely on heuristic-based injection positions.
Approach: They propose a method that extracts task-relevant representations from large language models and reinjects them during inference.
Outcome: The proposed method outperforms few-shot In-Context Learning (ICL) and LoRA methods without repeated demonstration processing.
Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptions (2025.findings-emnlp)

Copied to clipboard

Challenge: In-context learning has improved performance of large language models, but descriptive instructions are still under-explored.
Approach: They propose an ensemble prompt framework to describe selection criteria of multiple in-context examples. preliminary experiments on machine translation confirm that this framework boosts ICL performance.
Outcome: The proposed framework improves on commonsense, math, logical reasoning and hallucination tasks with three LLMs.
SCOI: Syntax-augmented Coverage-based In-context Example Selection for Machine Translation (2024.emnlp-main)

Copied to clipboard

Challenge: In-context learning improves performance of large language models (LLMs) performance of ICL highly depends on quality of demonstrations .
Approach: They propose a syntactic-augmented COverage-based In-context example selection strategy that leverages syntastic knowledge beyond word matching to select better examples for machine translation.
Outcome: The proposed strategy obtains the highest average COMET score among learning-free methods.
FuseSearch: Learning Adaptive Parallel Execution for Efficient Code Localization (2026.findings-acl)

Copied to clipboard

Challenge: Existing parallel code localization agents suffer from a 34.9% redundant tool invocation rate . specialized localization agent that operate as dedicated search components is needed to achieve high localization accuracy.
Approach: They propose a parallel code localization system that reframes parallel code execution as a quality–efficiency co-optimization problem.
Outcome: The proposed method matches SOTA performance while being 93.6% faster.

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