Search Results for author:
Found 21 papers, 14 papers with code
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
While many studies focus on evaluating the quality of end-to-end RAG systems, there is a lack of research on understanding the appropriateness of an LLM for the RAG task.
Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
To overcome these limitations, we propose Ferret, a novel approach that builds upon Rainbow Teaming by generating multiple adversarial prompt mutations per iteration and using a scoring function to rank and select the most effective adversarial prompt.
WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models
WalledEval is a comprehensive AI safety testing toolkit designed to evaluate large language models (LLMs).
DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
With the proliferation of domain-specific models, model merging has emerged as a set of techniques that combine the capabilities of multiple models into one that can multitask without the cost of additional training.
Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming
We propose Ruby Teaming, a method that improves on Rainbow Teaming by including a memory cache as its third dimension.
HyperTTS: Parameter Efficient Adaptation in Text to Speech using Hypernetworks
In this work, we present HyperTTS, which comprises a small learnable network, "hypernetwork", that generates parameters of the Adapter blocks, allowing us to condition Adapters on speaker representations and making them dynamic.
Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic
We demonstrate the effectiveness of RESTA in both parameter-efficient and full fine-tuning, covering a wide range of downstream tasks, including instruction following in Chinese, English, and Hindi, as well as problem-solving capabilities in Code and Math.
Adapter Pruning using Tropical Characterization
Adapters are widely popular parameter-efficient transfer learning approaches in natural language processing that insert trainable modules in between layers of a pre-trained language model.
Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases
On open-source models such as VICUNA-7B and LLAMA-2-CHAT 7B AND 13B, it shows an attack success rate of more than 91%.
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
In this work, we propose a new safety evaluation benchmark RED-EVAL that carries out red-teaming.
Ranked #1 on
Text Generation
on HarmfulQA
ReMask: A Robust Information-Masking Approach for Domain Counterfactual Generation
Our experiments empirically show that the counterfactual samples sourced from our masked text lead to improved domain transfer on 10 out of 12 domain sentiment classification settings, with an average of 2% accuracy improvement over the state-of-the-art for unsupervised domain adaptation (UDA).
A Review of Deep Learning Techniques for Speech Processing
The power of deep learning techniques has opened up new avenues for research and innovation in the field of speech processing, with far-reaching implications for a range of industries and applications.
Evaluating Parameter-Efficient Transfer Learning Approaches on SURE Benchmark for Speech Understanding
To mitigate this issue, parameter-efficient transfer learning algorithms, such as adapters and prefix tuning, have been proposed as a way to introduce a few trainable parameters that can be plugged into large pre-trained language models such as BERT, and HuBERT.
Adaptation Approaches for Nearest Neighbor Language Models
Semi-parametric Nearest Neighbor Language Models ($k$NN-LMs) have produced impressive gains over purely parametric LMs, by leveraging large-scale neighborhood retrieval over external memory datastores.
Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding
VIP particularly focuses on two aspects -- contextual prompts that learns input-specific contextualization of the soft prompt tokens through a small-scale sentence encoder and quantized prompts that maps the contextualized prompts to a set of learnable codebook vectors through a Vector quantization network.
KNOT: Knowledge Distillation using Optimal Transport for Solving NLP Tasks
We propose a new approach, Knowledge Distillation using Optimal Transport (KNOT), to distill the natural language semantic knowledge from multiple teacher networks to a student network.
Emotion Recognition in Conversation
Knowledge Distillation
+4
More Identifiable yet Equally Performant Transformers for Text Classification
In this work, we provide deeper theoretical analysis and empirical observations on the identifiability of attention weights.
Recognizing Emotion Cause in Conversations
We address the problem of recognizing emotion cause in conversations, define two novel sub-tasks of this problem, and provide a corresponding dialogue-level dataset, along with strong Transformer-based baselines.
Ranked #1 on
Recognizing Emotion Cause in Conversations
on RECCON
Investigating Gender Bias in BERT
As a result, predictions of downstream NLP models can vary noticeably by varying gender words, such as replacing "he" to "she", or even gender-neutral words.
Improving Aspect-Level Sentiment Analysis with Aspect Extraction
Aspect-based sentiment analysis (ABSA), a popular research area in NLP has two distinct parts -- aspect extraction (AE) and labeling the aspects with sentiment polarity (ALSA).
Twitter Homophily: Network Based Prediction of User's Occupation
In this paper, we investigate the importance of social network information compared to content information in the prediction of a Twitter user{'}s occupational class.
