Counter-storytelling is a powerful mechanism people use to challenge dominant narratives. Unlike other forms of counterspeech that have been widely studied in computational social science, counter-storytelling has largely been overlooked. Counter-stories are difficult to detect automatically; they are relational (defin...
Uma Sushmitha Gunturi, Jimin Mun, Maarten Sap et al.· 0 citations
Structured prediction tasks pose unique challenges for in-context learning (ICL): their compositional outputs require modeling fine-grained, token-level patterns that sentence-level approaches fail to capture, and their task-specific annotation conventions are human-defined artifacts that cannot be acquired through pre...
Fan Bai, Heng-Shuo Miao, S. Batra et al.· 0 citations
In a Transformer, token mixing is the step that lets each token draw information from other tokens, and it dominates the cost of encoding long sequences. Self-attention does this mixing very well: every token weighs every other token by content, which gives strong contextual modeling. That all-pairs comparison is also...
Rana Aref Salama, Abdou Youssef, Mona T. Diab· 0 citations
We investigate error discovery and handling in question answering over imperfect tables through controlled studies across three large language models (LLMs) on human-reviewed RADAR-T examples. Answering questions over these tables requires handling errors that can affect the answer. We vary row order and compare origin...
Baowen Zhang, Wei Fan, Ruman Wang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Activation steering has proven effective for controlling the behavior of Large Language Models (LLMs) at inference time, but its application to SpeechLLMs remains new, and training-free steering approaches for such models are still largely unexplored. We propose a training-free Contrastive Activation Addition (CAA) pro...
S\'everin Baroudi, Yanis Labrak, Pierfrancesco Melucci et al.· 0 citations
Detecting responses that retrieval-augmented generation does not ground in its context trades speed against accuracy: surface checks miss paraphrased fabrication, sampling-based methods cost extra generations. Hidden-state probes sit between the two, but every existing one reads the generating model's own activations,...
Michael Rathmayr, Adam Kovacs, Gábor Recski· 0 citations
The results point to a fidelity gap in AI-mediated communication, with implications for journalism, policy deliberation, scientific communication, and other domains where opinion-laden messages pass through language models.
Ling-Chong Liu, Yan-Fei Zhou, Jacob Bien et al.· 0 citations
Answer correctness is encoded as a recoverable geometric direction in the hidden states of language models. We show that the mean displacement from incorrect to correct answer representations, computed at approximately 70\% of model depth from fifty labeled examples with no parameter updates, yields a scoring direction...
M. Armstrong, Navid Ayoobi, Pradham Mummaleti et al.· 0 citations
Nowadays, emojis are often replacing words. Yet computational systems still oversimplify them. Most existing approaches treat emojis as static sentiment indicators and overlook their emotional distributions. In this study, we propose an emoji-aware emotion analysis framework based on a Twitter (X) dataset of 100,000 em...
Public vs. private universities is a debatable issue, and it creates polarization on social media in Bangladesh. Debate on quality, jobs, and prestige is passionate among the students, parents, and graduates, the majority of whom speak Bengali, a low-resource language. To measure this polarization, this paper introduce...
Safaruzzaman Shovo, Monowar Islam, A. Hossain et al.· 0 citations
Data quality now matters as much as compute for training language models. Much training data comes from human annotation of text, and interpretive annotation has no ground truth that could settle what is"accurate". Two lines of work respond to this. One combines annotators into a"ground truth"and measures how well they...
A coupled active-inference model of dialogue in which a listener's likelihood for an utterance is the policy distribution attributed to the speaker, placing the speaker's expected free energy within the listener's variational free energy.
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
