Search Results for author:
Found 15 papers, 8 papers with code
STeCa: Step-level Trajectory Calibration for LLM Agent Learning
To address this, we highlight the importance of timely calibration and the need to automatically construct calibration trajectories for training agents.
Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
The safety alignment of large language models (LLMs) remains vulnerable, as their initial behavior can be easily jailbroken by even relatively simple attacks.
TokenSkip: Controllable Chain-of-Thought Compression in LLMs
Chain-of-Thought (CoT) has been proven effective in enhancing the reasoning capabilities of large language models (LLMs).
Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
Large Language Models (LLMs) have revolutionized text generation, making detecting machine-generated text increasingly challenging.
Direct Preference Optimization Using Sparse Feature-Level Constraints
The alignment of large language models (LLMs) with human preferences remains a key challenge.
Subtle Errors Matter: Preference Learning via Error-injected Self-editing
In this work, we propose a novel preference learning framework called eRror-Injected Self-Editing (RISE), which injects predefined subtle errors into partial tokens of correct solutions to construct hard pairs for error mitigation.
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
Fine-tuning and in-context learning (ICL) are two prevalent methods in imbuing large language models with task-specific knowledge.
E2CL: Exploration-based Error Correction Learning for Embodied Agents
Language models are exhibiting increasing capability in knowledge utilization and reasoning.
AutoPal: Autonomous Adaptation to Users for Personal AI Companionship
However, imbuing agents with autonomous adaptability presents unique challenges, including identifying optimal adaptations to meet users' expectations and ensuring a smooth transition during the adaptation process.
No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks
In particular, we analyze the two most representative types of attack approaches: Explicit Harmful Attack (EHA) and Identity-Shifting Attack (ISA).
Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue
Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents.
Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback
An emotional support conversation system aims to alleviate users' emotional distress and assist them in addressing their challenges.
COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal
In recent years, there has been a growing interest in exploring dialogues with more complex goals, such as negotiation, persuasion, and emotional support, which go beyond traditional service-focused dialogue systems.
Self-Detoxifying Language Models via Toxification Reversal
Drawing on this idea, we devise a method to identify the toxification direction from the normal generation process to the one prompted with the negative prefix, and then steer the generation to the reversed direction by manipulating the information movement within the attention layers.
Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation
Target-oriented dialogue systems, designed to proactively steer conversations toward predefined targets or accomplish specific system-side goals, are an exciting area in conversational AI.
