Search Results for author:
Found 48 papers, 25 papers with code
“Let Your Characters Tell Their Story”: A Dataset for Character-Centric Narrative Understanding
When reading a literary piece, readers often make inferences about various characters’ roles, personalities, relationships, intents, actions, etc.
Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferences
Current LLMs are trained to refuse potentially harmful input queries regardless of whether users actually had harmful intents, causing a tradeoff between safety and user experience.
ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
When applied to the instruction-tuned Tulu3-8B model, ParaPO with system prompting successfully preserves famous quotation recall while reducing unintentional regurgitation (from 8. 7 to 6. 3 in creative writing) when prompted not to regurgitate.
Large-Scale Data Selection for Instruction Tuning
However, popular deployed instruction-tuned models often train on hundreds of thousands to millions of samples, subsampled from even larger data pools.
Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning
Large language models (LLMs) often fail to ask effective questions under uncertainty, making them unreliable in domains where proactive information-gathering is essential for decisionmaking.
IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance
Large language models (LLMs) are helping millions of users write texts about diverse issues, and in doing so expose users to different ideas and perspectives.
2 OLMo 2 Furious
Our modified model architecture and training recipe achieve both better training stability and improved per-token efficiency.
Multi-Attribute Constraint Satisfaction via Language Model Rewriting
Thus, we create Multi-Attribute Constraint Satisfaction (MACS), a generalized method capable of finetuning language models on any sequential domain to satisfy user-specified constraints on multiple external real-value attributes.
Tulu 3: Pushing Frontiers in Open Language Model Post-Training
Language model post-training is applied to refine behaviors and unlock new skills across a wide range of recent language models, but open recipes for applying these techniques lag behind proprietary ones.
RESTOR: Knowledge Recovery through Machine Unlearning
Large language models trained on web-scale corpora can memorize undesirable datapoints such as incorrect facts, copyrighted content or sensitive data.
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
We analyze features from the routing model to identify characteristics of instances that can benefit from human feedback, e. g., prompts with a moderate safety concern or moderate intent complexity.
HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions
AI agents are increasingly autonomous in their interactions with human users and tools, leading to increased interactional safety risks.
AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents
We design a set of realistic scenarios where language agents are instructed to achieve goals that are in conflict with being truthful during a multi-turn conversation with simulated human agents.
Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement
We present a principled approach to provide LLM-based evaluation with a rigorous guarantee of human agreement.
The Art of Saying No: Contextual Noncompliance in Language Models
Chat-based language models are designed to be helpful, yet they should not comply with every user request.
How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models
Given the growing influx of misinformation across news and social media, there is a critical need for systems that can provide effective real-time verification of news claims.
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
As WildJailbreak considerably upgrades the quality and scale of existing safety resources, it uniquely enables us to examine the scaling effects of data and the interplay of data properties and model capabilities during safety training.
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
For automated evaluation with WildBench, we have developed two metrics, WB-Reward and WB-Score, which are computable using advanced LLMs such as GPT-4-turbo.
Information-Theoretic Distillation for Reference-less Summarization
The current winning recipe for automatic summarization is using proprietary large-scale language models (LLMs) such as ChatGPT as is, or imitation learning from them as teacher models.
Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization
Our approach is to test several simple multi-LLM-agent architectures for customization, as well as an end-to-end LLM, using a new evaluation set, called CustomPlans, of over 200 WikiHow procedures each with a customization need.
MacGyver: Are Large Language Models Creative Problem Solvers?
We explore the creative problem-solving capabilities of modern LLMs in a novel constrained setting.
UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations
To instead investigate the ability to model unusual, unexpected, and unlikely situations, we explore the task of uncommonsense abductive reasoning.
STEER: Unified Style Transfer with Expert Reinforcement
We propose STEER: Unified Style Transfer with Expert Reinforcement, a unified frame-work developed to overcome the challenge of limited parallel data for style transfer.
In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search
To effectively use large language models (LLMs) for real-world queries, it is imperative that they generalize to the long-tail distribution, i. e. rare examples where models exhibit low confidence.
Agent Lumos: Unified and Modular Training for Open-Source Language Agents
To foster generalizable agent learning, we collect large-scale, unified, and high-quality training annotations derived from diverse ground-truth reasoning rationales across various complex interactive tasks.
The Generative AI Paradox: "What It Can Create, It May Not Understand"
Specifically, we propose and test the Generative AI Paradox hypothesis: generative models, having been trained directly to reproduce expert-like outputs, acquire generative capabilities that are not contingent upon -- and can therefore exceed -- their ability to understand those same types of outputs.
What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations
From this model we distill a high-quality dataset, \delta-Rules-of-Thumb, of 1. 2M entries of contextualizations and rationales for 115K defeasible moral actions rated highly by human annotators 85. 9% to 99. 8% of the time.
Creativity Support in the Age of Large Language Models: An Empirical Study Involving Emerging Writers
The development of large language models (LLMs) capable of following instructions and engaging in conversational interactions sparked increased interest in their utilization across various support tools.
PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning
We present PlaSma, a novel two-pronged approach to endow small language models with procedural knowledge and (constrained) language planning capabilities.
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
The Swift module is a small encoder-decoder LM fine-tuned on the oracle agent's action trajectories, while the Sage module employs LLMs such as GPT-4 for subgoal planning and grounding.
Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing
We present Impossible Distillation, a novel framework for paraphrasing and sentence summarization, that distills a high-quality dataset and model from a low-quality teacher that itself cannot perform these tasks.
Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning
While extreme-scale language models have demonstrated exceptional performance on a variety of language tasks, the degree of control over these language models through pure prompting can often be limited.
Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models
However, RLHF is an unstable and data-hungry process that continually requires new high-quality LM-generated data for finetuning.
Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation
We propose a new grounded keys-to-text generation task: the task is to generate a factual description about an entity given a set of guiding keys, and grounding passages.
NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarization
To encourage research in this direction, we propose NarraSum, a large-scale narrative summarization dataset.
Towards Inter-character Relationship-driven Story Generation
In this paper, we introduce the task of modeling interpersonal relationships for story generation.
Generating Sequences by Learning to Self-Correct
Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content.
REV: Information-Theoretic Evaluation of Free-Text Rationales
More concretely, we propose a metric called REV (Rationale Evaluation with conditional V-information), to quantify the amount of new, label-relevant information in a rationale beyond the information already available in the input or the label.
Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approach
In particular, we hypothesize that the order of the input concepts can affect the PTM's ability to utilize its commonsense knowledge.
Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations
Despite their impressive capabilities, large pre-trained language models (LMs) struggle with consistent reasoning; recently, prompting LMs to generate explanations that self-guide the inference has emerged as a promising direction to amend this.
Uncovering Implicit Gender Bias in Narratives through Commonsense Inference
Pre-trained language models learn socially harmful biases from their training corpora, and may repeat these biases when used for generation.
"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
When reading a literary piece, readers often make inferences about various characters' roles, personalities, relationships, intents, actions, etc.
Is Everything in Order? A Simple Way to Order Sentences
We perform evaluations in a zero-shot setting, showcasing that our model is able to generalize well across other datasets.
Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision
In this paper, we investigate the extent to which neural models can reason about natural language rationales that explain model predictions, relying only on distant supervision with no additional annotation cost for human-written rationales.
ParsiNLU: A Suite of Language Understanding Challenges for Persian
Despite the progress made in recent years in addressing natural language understanding (NLU) challenges, the majority of this progress remains to be concentrated on resource-rich languages like English.
Cue Me In: Content-Inducing Approaches to Interactive Story Generation
Previous approaches in this domain have focused largely on one-shot generation, where a language model outputs a complete story based on limited initial input from a user.
Modeling Protagonist Emotions for Emotion-Aware Storytelling
Emotions and their evolution play a central role in creating a captivating story.
