Search Results for author:
Found 41 papers, 31 papers with code
VisFactor: Benchmarking Fundamental Visual Cognition in Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have demonstrated remarkable advancements in multimodal understanding; however, their fundamental visual cognitive abilities remain largely underexplored.
Findings of the WMT 2024 Shared Task on Discourse-Level Literary Translation
Following last year, we have continued to host the WMT translation shared task this year, the second edition of the Discourse-Level Literary Translation.
DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization
To address this, we propose DRPruning, which incorporates distributionally robust optimization to restore balanced performance across domains, along with further improvements to enhance robustness.
On the Shortcut Learning in Multilingual Neural Machine Translation
By carefully designing experiments on different MNMT scenarios and models, we attribute the off-target issue to the overfitting of the shortcuts of (non-centric, centric) language mappings.
NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
Despite their remarkable abilities in various tasks, large language models (LLMs) still struggle with real-time information (e. g., new facts and terms) due to the knowledge cutoff in their development process.
Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step
To assess the safety of existing models, we introduce a novel jailbreaking method called Chain-of-Jailbreak (CoJ) attack, which compromises image generation models through a step-by-step editing process.
Learning to Ask: When LLM Agents Meet Unclear Instruction
Equipped with the capability to call functions, modern large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone.
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation (MLE) with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence.
CoAct: A Global-Local Hierarchy for Autonomous Agent Collaboration
Existing LLMs exhibit remarkable performance on various NLP tasks, but still struggle with complex real-world tasks, even equipped with advanced strategies like CoT and ReAct.
Improving Gloss-free Sign Language Translation by Reducing Representation Density
In this paper, we identify a representation density problem that could be a bottleneck in restricting the performance of gloss-free SLT.
Contrastive Learning
Gloss-free Sign Language Translation
+2
How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
Researchers have examined LLMs' decision-making through the lens of Game Theory.
Unsupervised Sign Language Translation and Generation
Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant single-modality (text and video) data without parallel sign language data.
Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model
In this work, we investigate the potential of employing the QE model as the reward model to predict human preferences for feedback training.
The Earth is Flat? Unveiling Factual Errors in Large Language Models
Current methods for evaluating LLMs' veracity are limited by test data leakage or the need for extensive human labor, hindering efficient and accurate error detection.
LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models
We introduce LogicAsker, a novel approach for evaluating and enhancing the logical reasoning capabilities of large language models (LLMs) such as ChatGPT and GPT-4.
Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models
Ideally, an advanced agent should possess the ability to accurately describe a given word using an aggressive description while concurrently maximizing confusion in the conservative description, enhancing its participation in the game.
Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models
This paper identifies a cultural dominance issue within large language models (LLMs) due to the predominant use of English data in model training (e. g., ChatGPT).
All Languages Matter: On the Multilingual Safety of Large Language Models
In this work, we build the first multilingual safety benchmark for LLMs, XSafety, in response to the global deployment of LLMs in practice.
Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench
Large Language Models (LLMs) have recently showcased their remarkable capacities, not only in natural language processing tasks but also across diverse domains such as clinical medicine, legal consultation, and education.
GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
We propose a novel framework CipherChat to systematically examine the generalizability of safety alignment to non-natural languages -- ciphers.
Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench
Evaluating Large Language Models' (LLMs) anthropomorphic capabilities has become increasingly important in contemporary discourse.
Revisiting the Reliability of Psychological Scales on Large Language Models
Recent research has focused on examining Large Language Models' (LLMs) characteristics from a psychological standpoint, acknowledging the necessity of understanding their behavioral characteristics.
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
To address the DoT problem, we propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of "tit for tat" and a judge manages the debate process to obtain a final solution.
Cross-modality Data Augmentation for End-to-End Sign Language Translation
To tackle these challenges, we propose a novel Cross-modality Data Augmentation (XmDA) framework to transfer the powerful gloss-to-text translation capabilities to end-to-end sign language translation (i. e. video-to-text) by exploiting pseudo gloss-text pairs from the sign gloss translation model.
Ranked #4 on
Sign Language Translation
on CSL-Daily
Exploring Human-Like Translation Strategy with Large Language Models
Compared to typical machine translation that focuses solely on source-to-target mapping, LLM-based translation can potentially mimic the human translation process which might take preparatory steps to ensure high-quality translation.
ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback
Therefore, we propose ParroT, a framework to enhance and regulate the translation abilities during chat based on open-source LLMs (e. g., LLaMA), human-written translation and feedback data.
ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark
ChatGPT is a cutting-edge artificial intelligence language model developed by OpenAI, which has attracted a lot of attention due to its surprisingly strong ability in answering follow-up questions.
Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine
By evaluating on a number of benchmark test sets, we find that ChatGPT performs competitively with commercial translation products (e. g., Google Translate) on high-resource European languages but lags behind significantly on low-resource or distant languages.
Adapters for Enhanced Modeling of Multilingual Knowledge and Text
Specifically, we introduce a lightweight adapter set to enhance MLLMs with cross-lingual entity alignment and facts from MLKGs for many languages.
Tencent's Multilingual Machine Translation System for WMT22 Large-Scale African Languages
This paper describes Tencent's multilingual machine translation systems for the WMT22 shared task on Large-Scale Machine Translation Evaluation for African Languages.
Scaling Back-Translation with Domain Text Generation for Sign Language Gloss Translation
In this paper, to overcome the limitation, we propose a Prompt based domain text Generation (PGEN) approach to produce the large-scale in-domain spoken language text data.
Understanding and Mitigating the Uncertainty in Zero-Shot Translation
Zero-shot translation is a promising direction for building a comprehensive multilingual neural machine translation~(MNMT) system.
Understanding and Improving Sequence-to-Sequence Pretraining for Neural Machine Translation
In this paper, we present a substantial step in better understanding the SOTA sequence-to-sequence (Seq2Seq) pretraining for neural machine translation~(NMT).
Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation
In this work, we propose to improve the sampling procedure by selecting the most informative monolingual sentences to complement the parallel data.
Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation
In addition, experimental results demonstrate that our Multi-Task NAT is complementary to knowledge distillation, the standard knowledge transfer method for NAT.
Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation
First, we train an identification model on the original training data, and use it to distinguish inactive examples and active examples by their sentence-level output probabilities.
Exploiting Unsupervised Data for Emotion Recognition in Conversations
Emotion Recognition in Conversations (ERC) aims to predict the emotional state of speakers in conversations, which is essentially a text classification task.
Emotion Recognition in Conversation
General Classification
+2
Real-Time Emotion Recognition via Attention Gated Hierarchical Memory Network
We propose an Attention Gated Hierarchical Memory Network (AGHMN) to address the problems of prior work: (1) Commonly used convolutional neural networks (CNNs) for utterance feature extraction are less compatible in the memory modules; (2) Unidirectional gated recurrent units (GRUs) only allow each historical utterance to have context before it, preventing information propagation in the opposite direction; (3) The Soft Attention for summarizing loses the positional and ordering information of memories, regardless of how the memory bank is built.
Ranked #49 on
Emotion Recognition in Conversation
on IEMOCAP
Improving Word Representations: A Sub-sampled Unigram Distribution for Negative Sampling
Word2Vec is the most popular model for word representation and has been widely investigated in literature.
PT-CoDE: Pre-trained Context-Dependent Encoder for Utterance-level Emotion Recognition
Witnessing the success of transfer learning in natural language process (NLP), we propose to pre-train a context-dependent encoder (CoDE) for ULER by learning from unlabeled conversation data.
HiGRU: Hierarchical Gated Recurrent Units for Utterance-level Emotion Recognition
In this paper, we address three challenges in utterance-level emotion recognition in dialogue systems: (1) the same word can deliver different emotions in different contexts; (2) some emotions are rarely seen in general dialogues; (3) long-range contextual information is hard to be effectively captured.
