This paper addresses the critical challenge of assessing the representativeness of news thumbnail images, which often serve as the first visual engagement for readers when an article is disseminated on social media. We focus on whether a news image represents the actors discussed in the news text. To serve the challenge, we introduce NewsTT, a manually annotated dataset of 1000 news thumbnail images and text pairs. We found that the pretrained vision and language models, such as BLIP-2, struggle with this task. Since news subjects frequently involve named entities or proper nouns, the pretrained models could have a limited capability to match news actors' visual and textual appearances. We hypothesize that learning to contrast news text with its counterfactual, of which named entities are replaced, can enhance the cross-modal matching ability of vision and language models. We propose CFT-CLIP, a contrastive learning framework that updates vision and language bi-encoders according to the hypothesis. We found that our simple method can boost the performance for assessing news thumbnail representativeness, supporting our assumption. Code and data can be accessed at https://github.com/ssu-humane/news-images-acl24.

Large language models (LLMs) demonstrate exceptional performance in numerous tasks but still heavily rely on knowledge stored in their parameters. Moreover, updating this knowledge incurs high training costs. Retrieval-augmented generation (RAG) methods address this issue by integrating external knowledge. The model can answer questions it couldn't previously by retrieving knowledge relevant to the query. This approach improves performance in certain scenarios for specific tasks. However, if irrelevant texts are retrieved, it may impair model performance. In this paper, we propose Retrieval Augmented Iterative Self-Feedback (RA-ISF), a framework that iteratively decomposes tasks and processes them in three submodules to enhance the model's problem-solving capabilities. Experiments show that our method outperforms existing benchmarks, performing well on models like GPT3.5, Llama2, significantly enhancing factual reasoning capabilities and reducing hallucinations.

This paper introduces a novel information-theoretic perspective on the relationship between prominent group fairness notions in machine learning, namely statistical parity, equalized odds, and predictive parity. It is well known that simultaneous satisfiability of these three fairness notions is usually impossible, motivating practitioners to resort to approximate fairness solutions rather than stringent satisfiability of these definitions. However, a comprehensive analysis of their interrelations, particularly when they are not exactly satisfied, remains largely unexplored. Our main contribution lies in elucidating an exact relationship between these three measures of (un)fairness by leveraging a body of work in information theory called partial information decomposition (PID). In this work, we leverage PID to identify the granular regions where these three measures of (un)fairness overlap and where they disagree with each other leading to potential tradeoffs. We also include numerical simulations to complement our results.

The study of population dynamics originated with early sociological works but has since extended into many fields, including biology, epidemiology, evolutionary game theory, and economics. Most studies on population dynamics focus on the problem of prediction rather than control. Existing mathematical models for control in population dynamics are often restricted to specific, noise-free dynamics, while real-world population changes can be complex and adversarial. To address this gap, we propose a new framework based on the paradigm of online control. We first characterize a set of linear dynamical systems that can naturally model evolving populations. We then give an efficient gradient-based controller for these systems, with near-optimal regret bounds with respect to a broad class of linear policies. Our empirical evaluations demonstrate the effectiveness of the proposed algorithm for control in population dynamics even for non-linear models such as SIR and replicator dynamics.

Imagine if the world's response to climate change relied solely on speculative predictions from pundits and CEOs, rather than the rigorous--though still imperfect--models of climate science. "Two degrees of warming will arrive soon-ish but will change the world less than we all think," one might say. "Two degrees of warming is not just around the corner. This is going to take a long time," another could counter. This is more or less the world we're in with artificial intelligence, with OpenAI CEO Sam Altman saying that AI systems that can do any task a human can will be developed in the "reasonably close-ish future," while Yann LeCun, Chief AI Scientist at Facebook, argues that human-level AI systems are "going to take a long time."

Before the start of India's general election in April, a top candidate looking to unseat Prime Minister Narendra Modi was not out wooing voters on the campaign trail. Arvind Kejriwal, the chief minister of Delhi and the head of a political party known for its anti-corruption platform, was arrested in late March for, yes, alleged corruption. His supporters hit the streets in protest, decrying the arrest as a politically motivated move by Modi aimed at weakening a rival. Soon after the arrest, Kejriwal implored his supporters to stay strong. "There are some forces who are trying to weaken our country and its democracy," he said in a 34-second audio clip posted to social media by a fellow party member.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. President Biden has shown signs of poor cognitive performance in private meetings with congressional lawmakers, as his age and mental acuity continue to come into question ahead of November's presidential election. Biden, 81, is the oldest person to hold the presidency and has faced skepticism from voters and Republican lawmakers about his ability to do his job. Many Republicans and even some Democrats said the president showed his age in private meetings, according to The Wall Street Journal, which spoke with 45 lawmakers and administration officials about the president's mental performance.

Charles Yeh's battle with disinformation in Taiwan began with a bowl of beef noodles. Nine years ago, the Taiwanese engineer was at a restaurant with his family when his mother-in-law started picking the green onions out of her food. Asked what she was doing, she explained that onions can harm your liver. She knew this, she said, because she had received text messages telling her so. Yeh was puzzled by this. His family had always happily eaten green onions.

Some Chinese artificial intelligence chip companies are now designing less-powerful processors to retain access to Taiwan Semiconductor Manufacturing Co. (TSMC) production in the face of U.S. sanctions, four people with knowledge of the matter said. Aiming to impede breakthroughs in AI and supercomputing by China's military, Washington has imposed a series of export controls on highly sophisticated processors from companies such as Nvidia and on chip manufacturing equipment. Those restrictions also prevent TSMC -- which uses U.S. chipmaking tools -- as well as other overseas chip manufacturers from taking orders to produce them. The most recent set of U.S. export controls imposed last October have exposed just how limited China's production capacity for advanced chips is and how dependent Chinese AI chip design companies are on TSMC -- the world's leading chip contract manufacturer, the sources said.

The Tokyo Metropolitan Government will launch its own dating app as early as this summer as part of government efforts to boost the dwindling national birthrate, an official said Tuesday. Users will be required to submit documentation proving they are legally single and sign a letter stating they are willing to get married. Stating one's income is common on Japanese dating apps, but Tokyo will require a tax certificate slip to prove the annual salary. "We learned that 70% of people who want to get married aren't actively joining events or apps to look for a partner," a Tokyo government official in charge of the new app said. "We want to give them a gentle push to find one."