Papers by Kexin Chen

12 papers
LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment (2026.acl-long)

Copied to clipboard

Challenge: Existing vector steering methods adjust the magnitude of answer vectors, but this creates a fundamental trade-off—reducing jailbreak increases over-refusal.
Approach: They propose a method which aligns va with vb through closed-form weight updates, making the model’s willingness to respond causally dependent on its safety assessment.
Outcome: Experiments on 12 LLMs show that the proposed method achieves 11.45% higher F1 than the best baseline while preserving 95.92% utility.
Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models (2025.acl-long)

Copied to clipboard

Challenge: Sticky tokens, when repeatedly inserted into sentences, pull sentence similarity toward a certain value, disrupting the normal distribution of embedding distances and degrading downstream performance.
Approach: They propose a method to detect “sticky tokens” by sentence and token filtering and apply it to 40 checkpoints across 14 model families.
Outcome: The proposed method detects 868 sticky tokens across 14 models and shows that their presence does not correlate with model size or vocabulary size.
ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting (2025.acl-long)

Copied to clipboard

Challenge: Contract clause retrieval is critical to contract drafting because of its high quality and complexity.
Approach: They propose the first expert-annotated benchmark specifically designed for contract clause retrieval . ACORD focuses on complex contract clauses such as Limitation of Liability, Indemnification, Change of Control .
Outcome: The atticus clause retrieval dataset shows promising results but needs improvement . the benchmark can be used as an IR benchmark for the NLP community .
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach: They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome: The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.
Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods to watermark low-entropy content are expensive and risky . IE reduces parameter size by 99% while achieving performance on par with state-of-the-art methods .
Approach: They propose a logit-based watermarking paradigm that uses entropy-based features to predict whether the next token is high or low.
Outcome: The proposed method reduces parameter size by 99% while achieving performance on par with state-of-the-art methods.
GCPG: A General Framework for Controllable Paraphrase Generation (2022.findings-acl)

Copied to clipboard

Challenge: Existing studies highlight a special condition under two indispensable aspects of controllable paraphrase generation (CPG) individually, lacking a unified circumstance to explore and analyze their effectiveness.
Approach: They propose a general controllable paraphrase generation framework that integrates lexical and syntactical conditions into a text sequence and uniformly processes them in an encoder-decoder paradigm.
Outcome: The proposed framework can combine lexical and syntactical conditions and improve paraphrase generation.
From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMs (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to unlearning often treat nonsensical responses or template-based refusals as the unlearning target, making the process even more vulnerable to attacks and jailbreaks.
Approach: They propose a method that uses inverted facts to remove the need for auxiliary models or retaining data while avoiding leakage.
Outcome: Evaluated on the ToFU Knowledge Unlearning dataset using Llama2-7B-Chat and Phi-1.5, MEOW outperforms baselines in forgetting quality while preserving model utility.
Tailor: A Soft-Prompt-Based Approach to Attribute-Based Controlled Text Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing work focuses on generating sentences satisfying pre-specified attributes such as topic and sentiment, yet suffers from increases in storage and inference time.
Approach: They propose a method that uses a pre-trained continuous vector to generate a fixed pre-trainable language model to satisfy a specified attribute.
Outcome: The proposed model can achieve improvements on eleven attribute-specific generation tasks with 0.08% extra training parameters.
ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Emotion Support Conversation (ESC) is a crucial application for reducing stress and providing emotional guidance.
Approach: They re-organize 2,801 role-playing cards to define roles of role-players . they train a specific role- playing model called ESC-Role which behaves more like a confused person than GPT-4 .
Outcome: The proposed model behaves more like a confused person than GPT-4, and the model performs better than GPLs.
SEER: Facilitating Structured Reasoning and Explanation via Reinforcement Learning (2024.acl-long)

Copied to clipboard

Challenge: Existing methods focus on single-step reasoning, ignoring logical dependencies between steps.
Approach: They propose a method that maximizes a structure-based return to facilitate structured reasoning and explanation.
Outcome: The proposed method outperforms state-of-the-art methods on EntailmentBank and STREET benchmarks.
Conflict-Aware Memory for Embodied Agents: Enhancing Vector Data Quality via Detection Rules (2026.acl-long)

Copied to clipboard

Challenge: Embodied agents have successfully leveraged large language models (LLMs) to better transform human instructions and images into executable task plans.
Approach: They propose Conflict Detection Rules to identify and manage data quality issues in vector knowledge bases and correct the index structure.
Outcome: Experimental results show that planners with Conflict Detection Rules exceed the basic LLM planner by 15.25% and 14.25% in grammatical accuracy (GA) and interpretation accuracy (IA) on average.
Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing research often overlooks the data quality issues within retrieval results, often caused by inaccurate existing vector-distance-based retrieval methods.
Approach: They propose to use Context-Driven Index Trimming framework to capture and regulate consistency between retrieved contexts and modify indexes in the database.
Outcome: Experiments show that the proposed framework can improve answer quality by 3.75% on open-domain question-answering tasks.

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