Related papers: Extending RECAST for Truth-Level Reinterpretations
Parameter-efficient finetuning (PEFT) methods seek to adapt large neural models via updates to a small number of weights. However, much prior interpretability work has shown that representations encode rich semantic information, suggesting…
Meta-analysis is routinely performed in many scientific disciplines. This analysis is attractive since discoveries are possible even when all the individual studies are underpowered. However, the meta-analytic discoveries may be entirely…
The last decade has seen tremendous progress in AI technology and applications. With such widespread adoption, ensuring the reliability of the AI models is crucial. In past, we took the first step of creating a testing framework called…
Interactive constraint systems often suffer from infeasibility (no solution) due to conflicting user constraints. A common approach to recover infeasibility is to eliminate the constraints that cause the conflicts in the system. This…
The recent adoption of machine learning as a tool in real world decision making has spurred interest in understanding how these decisions are being made. Counterfactual Explanations are a popular interpretable machine learning technique…
Algorithmic recourse is a process that leverages counterfactual explanations, going beyond understanding why a system produced a given classification, to providing a user with actions they can take to change their predicted outcome.…
Retrieval-augmented generation supports language models to strengthen their factual groundings by providing external contexts. However, language models often face challenges when given extensive information, diminishing their effectiveness…
Neurons in auto-regressive language models like GPT-2 can be interpreted by analyzing their activation patterns. Recent studies have shown that techniques such as dictionary learning, a form of post-hoc sparse coding, enhance this…
Supervised machine learning often operates on the data-driven paradigm, wherein internal model parameters are autonomously optimized to converge predicted outputs with the ground truth, devoid of explicitly programming rules or a priori…
Retrieval Augmented Generation (RAG) systems, despite their growing popularity for enhancing model response reliability, often struggle with trustworthiness and explainability. In this work, we present a novel, holistic, model-agnostic,…
In document-level event extraction (DEE) task, event arguments always scatter across sentences (across-sentence issue) and multiple events may lie in one document (multi-event issue). In this paper, we argue that the relation information of…
Aligned language models face a significant limitation as their fine-tuning often results in compromised safety. To tackle this, we propose a simple method RESTA that performs LLM safety realignment. RESTA stands for REstoring Safety through…
Existing benchmarks for evaluating mathematical reasoning in large language models (LLMs) rely primarily on competition problems, formal proofs, or artificially challenging questions -- failing to capture the nature of mathematics…
Recent work has shown that the computations of Transformers can be simulated in the RASP family of programming languages. These findings have enabled improved understanding of the expressive capacity and generalization abilities of…
We argue that the analysis of agent/environment interactions should be extended to include the conventions and invariants maintained by agents throughout their activity. We refer to this thicker notion of environment as a lifeworld and…
Context: Domain-specific languages (DSLs) enable domain experts to specify tasks and problems themselves, while enabling static analysis to elucidate issues in the modelled domain early. Although language workbenches have simplified the…
Large Language Models (LLMs) exhibit impressive results across a wide range of natural language processing (NLP) tasks, yet they can often produce factually incorrect outputs. This paper introduces a simple but effective low-latency…
End-to-end simultaneous speech translation (SST), which directly translates speech in one language into text in another language in real-time, is useful in many scenarios but has not been fully investigated. In this work, we propose…
Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for optimizing these emergent tool-use policies, yet the…
Sequential Recommendation (SR) aims to predict the next interaction of a user based on their behavior sequence, where complementary relations often provide essential signals for predicting the next item. However, mainstream models relying…