◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Xiang Lisa Li

Stanford University

14 papers hereh-index 1415.7k citations28 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author6
  • middle author8

Across the 14 of 14 papers where every author was matched, so the position is known.

fields
  • cs.CL12
  • cs.CV1
  • cs.LG1
affiliations
  • Stanford University
  • Johns Hopkins University
Homepage
same name
  • Xiang Lisa Li — 6 papers, h 7

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20192023
most citedPrefix-Tuning: Optimizing Continuous Prompts for Generation

293 citations · 670 across the 10 of their papers we have counts for

collaborators
Showing 2022Show all

4 papers · 1 filter

cs.CL2022★ 57 cited

Evaluating Human-Language Model Interaction

Mina Lee, Megha Srivastava, Amelia Hardy +15

Many real-world applications of language models (LMs), such as writing assistance and code autocomplete, involve human-LM interaction. However, most benchmarks are non-interactive…

cs.CL2022★ 8 cited

Contrastive Decoding: Open-ended Text Generation as Optimization

Xiang Lisa Li, Ari Holtzman, Daniel Fried +5

Given a language model (LM), maximum probability is a poor decoding objective for open-ended generation, because it produces short and repetitive text. On the other hand, sampling…

cs.CL2022★ 238 cited

Diffusion-LM Improves Controllable Text Generation

Xiang Lisa Li, John Thickstun, Ishaan Gulrajani +2

Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation. While recent works have demonstrated successes on cont…

cs.CL2022

TempLM: Distilling Language Models into Template-Based Generators

Tianyi Zhang, Mina Lee, Lisa Li +2

While pretrained language models (PLMs) have greatly improved text generation, they have also been known to produce unfaithful or inappropriate content. In contrast, classic templa…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.