2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
It is shown that models can be trained to implicitly identify influential factors and disclose them, offering a scalable path toward reducing unfaithful reasoning in LLMs.
The analysis shows that CoTs do not reliably track visual evidence that influences model predictions, and it is found that Predict-then-Explain explanations align more strongly with perturbation-induced probability shifts than pre-answer CoTs, while binary vCT scores are often nearly saturated.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
