Combating misinformation in the age of llms: Opportunities and challenges
Misinformation such as fake news and rumors is a serious threat on information ecosystems
and public trust. The emergence of Large Language Models (LLMs) has great potential to …
and public trust. The emergence of Large Language Models (LLMs) has great potential to …
Large language models for information retrieval: A survey
As a primary means of information acquisition, information retrieval (IR) systems, such as
search engines, have integrated themselves into our daily lives. These systems also serve …
search engines, have integrated themselves into our daily lives. These systems also serve …
Improving factual consistency for knowledge-grounded dialogue systems via knowledge enhancement and alignment
Pretrained language models (PLMs) based knowledge-grounded dialogue systems are
prone to generate responses that are factually inconsistent with the provided knowledge …
prone to generate responses that are factually inconsistent with the provided knowledge …
Rethinking Conversational Agents in the Era of LLMs: Proactivity, Non-collaborativity, and Beyond
Conversational systems are designed to offer human users social support or functional
services through natural language interactions. Typical conversation researches mainly …
services through natural language interactions. Typical conversation researches mainly …
Large Language Model Powered Agents for Information Retrieval
The vital goal of information retrieval today extends beyond merely connecting users with
relevant information they search for. It also aims to enrich the diversity, personalization, and …
relevant information they search for. It also aims to enrich the diversity, personalization, and …
Aligning Uncertainty: Leveraging LLMs to Analyze Uncertainty Transfer in Text Summarization
Automatically generated summaries can be evaluated along different dimensions, one being
how faithfully the uncertainty from the source text is conveyed in the summary. We present a …
how faithfully the uncertainty from the source text is conveyed in the summary. We present a …
HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild
Hallucinations pose a significant challenge to the reliability of large language models
(LLMs) in critical domains. Recent benchmarks designed to assess LLM hallucinations …
(LLMs) in critical domains. Recent benchmarks designed to assess LLM hallucinations …
KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
Despite their success at many natural language processing (NLP) tasks, large language
models (LLMs) still struggle to effectively leverage knowledge for knowledge-intensive tasks …
models (LLMs) still struggle to effectively leverage knowledge for knowledge-intensive tasks …
ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models
Large language models (LLMs) have achieved unprecedented performance in various
applications, yet their evaluation remains a critical issue. Existing hallucination benchmarks …
applications, yet their evaluation remains a critical issue. Existing hallucination benchmarks …
Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models
As large language models (LLMs) increasingly permeate daily lives, there is a growing
demand for real-time interactions that mirror human conversations. Traditional turn-based …
demand for real-time interactions that mirror human conversations. Traditional turn-based …