Search Results for author:
Found 25 papers, 15 papers with code
EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning
Large Language Models (LLMs) have shown impressive reasoning capabilities in well-defined problems with clear solutions, such as mathematics and coding.
OpenOmni: Large Language Models Pivot Zero-shot Omnimodal Alignment across Language with Real-time Self-Aware Emotional Speech Synthesis
In the alignment phase, a pre-trained speech model is further trained on text-image tasks to generalize from vision to speech in a (near) zero-shot manner, outperforming models trained on tri-modal datasets.
SDPO: Segment-Level Direct Preference Optimization for Social Agents
To address these limitations, we propose Segment-Level Direct Preference Optimization (SDPO), which focuses on specific key segments within interactions to optimize multi-turn agent behavior while minimizing training noise.
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct
This framework iteratively improve data quality through a refined combination of fine-grained perception, cognitive reasoning, and interaction evolution, generating a more complex and diverse image-text instruction dataset that empowers MLLMs with enhanced capabilities.
FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
Motivated by this, we formalize different formats of workflow knowledge and present FlowBench, the first benchmark for workflow-guided planning.
A Survey on Self-Evolution of Large Language Models
To address this issue, self-evolution approaches that enable LLM to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing.
Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
As intelligent agents, LLMs need to have the capabilities of task planning, long-term memory, and the ability to leverage external tools to achieve satisfactory performance.
Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
We observe that adapter tuning demonstrates superiority over prompt-based methods, even without parameter expansion in each learning session.
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
Furthermore, it is complementary to existing methods.
Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use
Specifically, the crucial information in the context will be potentially overlooked by model when it is positioned in the trough zone of the attention waveform, leading to decreased performance.
Ranked #2 on
Trajectory Planning
on ToolBench
Improving Factual Consistency of Text Summarization by Adversarially Decoupling Comprehension and Embellishment Abilities of LLMs
Despite the recent progress in text summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known as "hallucinations" in text generation.
Constructive Large Language Models Alignment with Diverse Feedback
This limitation leads to suboptimal performance, even when ample training data is available.
Self-Explanation Prompting Improves Dialogue Understanding in Large Language Models
Task-oriented dialogue (TOD) systems facilitate users in executing various activities via multi-turn dialogues, but Large Language Models (LLMs) often struggle to comprehend these intricate contexts.
UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt
Using the high-quality prompts generated, we scale the corpus of the pre-trained conversation model to 122 datasets from 15 dialog-related tasks, resulting in Universal Pre-trained Conversation Model (UniPCM), a powerful foundation model for various conversational tasks and different dialog systems.
UniSA: Unified Generative Framework for Sentiment Analysis
Sentiment analysis is a crucial task that aims to understand people's emotional states and predict emotional categories based on multimodal information.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents
SpokenWOZ further incorporates common spoken characteristics such as word-by-word processing and reasoning in spoken language.
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
In this paper, we propose Speech-text dialog Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialog pre-training model.
Ranked #2 on
Multimodal Sentiment Analysis
on CMU-MOSI
(Acc-2 metric, using extra
training data)
cross-modal alignment
Emotion Recognition in Conversation
+2
Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation
Dialogue Topic Segmentation (DTS) plays an essential role in a variety of dialogue modeling tasks.
Empathetic Response Generation via Emotion Cause Transition Graph
Empathetic dialogue is a human-like behavior that requires the perception of both affective factors (e. g., emotion status) and cognitive factors (e. g., cause of the emotion).
UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition
Multimodal sentiment analysis (MSA) and emotion recognition in conversation (ERC) are key research topics for computers to understand human behaviors.
Ranked #2 on
Multimodal Sentiment Analysis
on CMU-MOSI
CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation
Practical dialog systems need to deal with various knowledge sources, noisy user expressions, and the shortage of annotated data.
Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems
In this paper, we present Duplex Conversation, a multi-turn, multimodal spoken dialogue system that enables telephone-based agents to interact with customers like a human.
Aligning Logits Generatively for Principled Black-Box Knowledge Distillation
Black-Box Knowledge Distillation (B2KD) is a formulated problem for cloud-to-edge model compression with invisible data and models hosted on the server.
A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots
We find some new linguistic phenomena and interactive manners in SSTOD which raise critical challenges of building dialog agents for the task.
Ranked #1 on
SSTOD
on SSD_NAME
GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection
Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems.
Ranked #1 on
End-To-End Dialogue Modelling
on MULTIWOZ 2.0
