paper-with-me

Papers

Towards leveraging LLMs for Conditional QA

2023-12-02 · Syed-Amad Hussain, Parag Pravin Dakle, SaiKrishna Rallabandi, Preethi Raghavan

This study delves into the capabilities and limitations of Large Language Models (LLMs) in the challenging domain of conditional question-answering. Utilizing the Conditional Question Answering (CQA) dataset and focusing on generative models like T5 and UL2, we assess the performance of LLMs across diverse question types. Our findings reveal that fine-tuned LLMs can surpass the state-of-the-art (SOTA) performance in some cases, even without fully encoding all input context, with an increase of 7-8 points in Exact Match (EM) and F1 scores for Yes/No questions. However, these models encounter challenges in extractive question answering, where they lag behind the SOTA by over 10 points, and in mitigating the risk of injecting false information. A study with oracle-retrievers emphasizes the critical role of effective evidence retrieval, underscoring the necessity for advanced solutions in this area. Furthermore, we highlight the significant influence of evaluation metrics on performance assessments and advocate for a more comprehensive evaluation framework. The complexity of the task, the observed performance discrepancies, and the need for effective evidence retrieval underline the ongoing challenges in this field and underscore the need for future work focusing on refining training tasks and exploring prompt-based techniques to enhance LLM performance in conditional question-answering tasks.

📄 PDF Abstract BibTeX arXiv:2312.01143

Code (0)

등록된 구현이 없습니다.

Tasks

Extractive Question-AnsweringQuestion AnsweringRetrieval

Methods 이 논문이 사용한 방법론

Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adafactor Adafactor is a stochastic optimization method based on Adam that reduces memory usage while retaining the empirical benefits of…
Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods

2024-06-23 · Roy Xie, Junlin Wang, Ruomin Huang, Minxing Zhang 외

The rapid scaling of large language models (LLMs) has raised concerns about the transparency and fair use of the pretraining data used for training them. Detecting such content is challenging due to the scale of the data…

Inference AttackLanguage ModelingLanguage ModellingMembership Inference Attack

Diffusion LLMs are Natural Adversaries for any LLM

2025-10-31 · David Lüdke, Tom Wollschläger, Paul Ungermann, Stephan Günnemann 외 arxiv

We introduce a novel framework that transforms the resource-intensive (adversarial) prompt optimization problem into an \emph{efficient, amortized inference task}. Our core insight is that pretrained, non-autoregressive …

Red Teaming

Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment

2025-02-17 · Jingcheng Deng, Zhongtao Jiang, Liang Pang, Liwei Chen 외

A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently generative and distributive, conflicting wi…

Contrastive Learning

Leveraging LLMs to Create a Haptic Devices' Recommendation System

2025-01-22 · Yang Liu, Haiwei Dong, Abdulmotaleb El Saddik

Haptic technology has seen significant growth, yet a lack of awareness of existing haptic device design knowledge hinders development. This paper addresses these limitations by leveraging advancements in Large Language M…

Benchmarking

LayoutCoT: Unleashing the Deep Reasoning Potential of Large Language Models for Layout Generation

2025-04-15 · Hengyu Shi, Junhao Su, Huansheng Ning, Xiaoming Wei 외

Conditional layout generation aims to automatically generate visually appealing and semantically coherent layouts from user-defined constraints. While recent methods based on generative models have shown promising result…

In-Context LearningLayout GenerationRAGRetrieval+1