Papers by Jiayi Xie
Chronos: Learning Temporal Dynamics of Reasoning Chains for Test-Time Scaling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for testing time scales treat reasoning traces or tokens equally, ignoring substantial variations in trajectory quality and localized logical failures. |
| Approach: | They propose a chronological reasoning scorer that models each trajectory as a time series. |
| Outcome: | The proposed method achieves relative improvements of 34.21% over Pass@128 and 22.70% over Maj@135 on HMMT25, highlighting its effectiveness. |
Dagger Behind Smile: Fool LLMs with a Happy Ending Story (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have attracted significant attention from jailbreak attacks . existing manual designs are either easily detectable or require intricate interactions with LLMs. |
| Approach: | They propose a happy ending attack that wraps up a malicious request in a scenario template . |
| Outcome: | The proposed attack wraps up a malicious request in a scenario template involving a positive prompt formed mainly via a happy ending, fooling LLMs into jailbreaking either immediately or at a follow-up malicious request. |
Automated Essay Scoring via Pairwise Contrastive Regression (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to automate essay scoring use regression or ranking objectives . a novel neural pairwise ranking model is developed to optimize both objectives based on the same loss . |
| Approach: | They propose a novel Neural Pairwise Contrastive Regression model that optimizes both objectives simultaneously as a single loss. |
| Outcome: | The proposed model outperforms previous methods on the public Automated Student Assessment Prize dataset. |
Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs). |
| Approach: | They propose a model-free method that refines credit assignment by leveraging the model's internal uncertainty signals. |
| Outcome: | Extensive experiments on five mathematical reasoning benchmarks show that the proposed method outperforms strong RLVR baselines on multiple model scales, including 1.5B and 7B. |