Papers by Jianwei Yin

13 papers
Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are trained on vast corpora that contain substantial knowledge but their outputs often contain confidently stated inaccuracies.
Approach: They propose to encode truthfulness as a distinct linear feature, termed the "truth direction", which can classify truthfulness reliably.
Outcome: The proposed model can generalize to logical transformations, question-answering tasks, in-context learning, and external knowledge sources.
The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding? (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to self-improvement rely on external supervision signals in the form of seed data and/or assistance from third-party models.
Approach: They propose a framework for generating high-quality synthetic question-answer data in a fully autonomous manner.
Outcome: The proposed framework generates high-quality synthetic question-answer data in a fully autonomous manner.
GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies have demonstrated that supervised fine-tuning and reinforcement learning are effective in integrating knowledge injection with robust generalization.
Approach: They propose a unified post-training framework that addresses intrinsic limitations of supervised fine-tuning and reinforcement learning.
Outcome: The proposed framework surpasses SFT-based methods and yields policies that integrate more smoothly with subsequent RL training.
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback (2024.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated excellent performance in numerous tasks but the parameterized knowledge stored within LLMs may be incomplete and hard to incorporate up-to-date knowledge.
Approach: They propose a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model’s problem-solving capabilities.
Outcome: The proposed method outperforms existing benchmarks on GPT3.5, Llama2 and other large language models significantly enhancing factual reasoning capabilities and reducing hallucinations.
Explainable Quantum Program Repair with Verifiable Proof Traces (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to program repair provide only post-hoc, non-verifiable explanations that are not executable or verifiably.
Approach: They propose a framework that couples repair generation with machine-checkable executable explanations for quantum programs where correctness hinges on subtle semantic properties such as circuit equivalence and fidelity preservation.
Outcome: Experiments on QASMBench with mutation-generated quantum program bugs show that the proposed framework improves both semantic precision and explanation faithfulness over baselines that rely on unconstrained or purely natural-language explanations.
ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration (2025.emnlp-main)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) have shown impressive capabilities in vision-language understanding but their visual input remains fixed throughout the reasoning process.
Approach: They propose a model-agnostic tree search algorithm tailored for vision-level reasoning that allows MLLMs to explore textual tokens while visual input remains fixed throughout reasoning process.
Outcome: The proposed algorithm outperforms strong large models such as GPT-4o on high-resolution benchmarks and improves performance on a series of elaborate high-level benchmarks.
RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods to generate RAG documents require knowledge of the target RAG system’s internal composition and implementation details, whereas black-box methods are unable to utilize interactive information.
Approach: They propose a RIPRAG attack framework that treats the target RAG system as a black box and leverages a Reinforcement Learning from Black-box Feedback (RLBF) method to optimize the generation model for poisoned documents.
Outcome: The proposed method achieves an attack success rate (ASR) improvement of up to 0.72 compared to baseline methods.
CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing (2025.emnlp-main)

Copied to clipboard

Challenge: Open-source code language models (code LMs) are a growing threat for intellectual property protection.
Approach: They propose a black-box code LM watermarking framework that uses rule-based watermarks and utility-preserving injection method for user-level model tracing.
Outcome: The proposed framework shows that it performs well across multiple state-of-the-art code LMs and is harmless compared to existing baselines.
SAME: Signer-Aware Mixture-of-Experts for Test-Time Adaptation in Sign Language Translation (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for supervised fine-tuning are limited due to labeled data . existing methods require long adaptation times and batch statistics are unavailable in streaming settings .
Approach: They propose a plug-and-play, signer-aware Mixture-of-Experts (MoE) TTA architecture for SLT . they use a combination of lightweight MoE modules and unsupervised regularizers to decouple domain shift .
Outcome: The proposed test-time adaptation outperforms existing TTA methods in sign language translation . the proposed architecture can be used in real-world deployments without labeling .
An Explainable Toolbox for Evaluating Pre-trained Vision-Language Models (2022.emnlp-demos)

Copied to clipboard

Challenge: Existing studies evaluate VLP models by comparing the fine-tuned downstream task performance with the average downstream task accuracy.
Approach: They propose a toolbox for evaluating Vision-Language Pretraining (VLP) models.
Outcome: The proposed toolbox provides the preliminary datasets that deepen the image-texting ability of a VLP model.
ToolGate: Contract-Grounded and Verified Tool Execution for LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Existing frameworks for tool-augmented LLMs rely heavily on natural language reasoning to determine when tools can be invoked and whether their results should be trusted.
Approach: They propose a forward execution framework that provides logical safety guarantees and verifiable state evolution for LLM tool calling.
Outcome: The proposed framework improves the reliability and verifiability of tool-augmented LLM systems while maintaining competitive performance on multi-step reasoning tasks.
SecCoder: Towards Generalizable and Robust Secure Code Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Existing secure code generation methods have limited generalizability to unseen test cases and poor robustness against the attacked model, leading to safety failures in code generation.
Approach: They propose a generalizable and robust secure code generation method SecCoder by using in-context learning and the safe demonstration.
Outcome: The proposed method achieves a significant security improvement of 7.20% on unseen test cases and better robustness against the attacked model.
ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis (2024.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable in-context learning capabilities in various natural language processing tasks.
Approach: They propose a novel approach ERA-CoT which aids LLMs in understanding context by capturing relationships between entities and supports the reasoning of diverse tasks through Chain-of-Thoughts (CoT).
Outcome: The proposed method improves on GPT3.5 and previous SOTA prompting methods by an average of 5.1% compared to previous prompting approaches.

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