7 accepted papers
LLM parameter editing methods commonly rely on computing an ideal target hidden-state at a target layer (referred as anchor point) and distributing the target vector to multiple preceding layers (commonly known as backward spreading) for cooperative editing. Although widely used for a long time, its…
This study investigates the self-rationalization framework constructed with a cooperative game, where a generator initially extracts the most informative segment from raw input, and a subsequent predictor utilizes the selected subset for its input. The generator and predictor are trained collaborati…
Extracting a small subset of crucial rationales from the full input is a key problem in explainability research. The most widely used fundamental criterion for rationale extraction is the maximum mutual information (MMI) criterion. In this paper, we first demonstrate that MMI suffers from diminishin…
An important line of research in the field of explainability is to extract a small subset of crucial rationales from the full input. The most widely used criterion for rationale extraction is the maximum mutual information (MMI) criterion. However, in certain datasets, there are spurious features no…
The lack of interaction data of new items in recommendation systems leads to the problem of cold-start item recommendations. Current methods usually approximate content features of the items to interaction embeddings and then use content features for prediction. However, these methods typically lear…
Rationalization aims to strengthen the interpretability of NLP models by extracting a subset of human-intelligible pieces of their inputting texts. Conventional works generally employ the maximum mutual information (MMI) criterion to find the rationale that is most indicative of the target label. Ho…
Next-basket recommendation (NBR) is a type of recommendation task that focuses on mining user interests based on the sequential basket records in which users purchase multiple items at a time. Limited by the sparsity brought by short-term user interaction behavior, existing NBR methods typically fai…