Papers with AGR

4 papers
AGR: Reinforced Causal Agent-Guided Self-explaining Rationalization (2024.acl-short)

Copied to clipboard

Challenge: Existing rationalization approaches are susceptible to degeneration due to lack of effective control over the learning direction of the model during training.
Approach: They propose an agent-guided rationalization approach that guides the next step of the model based on its current training state.
Outcome: The proposed approach outperforms state-of-the-art methods on BeerAdvocate and HotelReview datasets.
Generative-to-Discriminative Test-Time Adaptation via Manifold-Aware Diffusion and Bayesian Distillation (2026.findings-acl)

Copied to clipboard

Challenge: Existing discriminative approaches suffer from "confident but wrong" failure mode, blindly adapting to OOD noise leading to error accumulation.
Approach: They propose a TTA framework that harmonizes the robustness of generative diffusion models with the efficiency of discriminative regression networks via Bayesian Diffusion Distillation (BDD).
Outcome: The proposed framework reduces MAE from 0.6872 to 0.5673 and boosts binary accuracy by 5.81 percentage points (reaching 57.33%) it also reduces the MAE of the MOSI to SIMS shift and achieves an 11.18-point gain over the baseline.
Open-Domain Why-Question Answering with Adversarial Learning to Encode Answer Texts (P19-1)

Copied to clipboard

Challenge: Existing why-QA methods retrieve “answer passages” that consist of several sentences . AGR is a vector representation of the non-redundant reason sought by a why-question .
Approach: They propose a method for why-question answering that uses an adversarial learning framework.
Outcome: The proposed method improves state-of-the-art open-domain QA on Japanese datasets . it also improves a state- of-the art method on publicly available English datasets.
Analyze, Generate and Refine: Query Expansion with LLMs for Zero-Shot Open-Domain QA (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods like GAR and EAR rely heavily on supervised training and struggle to maintain effectiveness across domains and datasets.
Approach: They propose a QE approach based on a three-step prompting strategy to enhance query expansion by broadening the scope of queries with additional relevant texts.
Outcome: The proposed approach outperforms state-of-the-art methods in out-domain zero-shot scenarios and outperformed existing methods in end-to-end evaluations.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations