Prasanna Parthasarathi

2025-10-15

NeurIPS.cc/2025/Workshop/ER (accepted)

GRPO-λ: Credit Assignment improves LLM Reasoning

Mathieu Reymond

Boxing Chen

Yufei Cui

A. Chandar

Large language models (LLMs) are increasingly deployed for tasks requiring complex reasoning, prompting significant interest in improving th… (see more)eir reasoning abilities through post-training. Especially RL based methods using verifiable reward, like the state-of-the-art GRPO, have shown to tremendously improve reasoning behaviors when applied as post-training methods. However, the lack of an explicit reward or critic model limits GRPO's ability to assign fine-grained credit across token sequences. In this work, we present GRPO-

2025-09-29

ArXiv (preprint)

Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination

Mehdi Rezagholizadeh

Boxing Chen

A. Chandar

The growth in prominence of large language models (LLMs) in everyday life can be largely attributed to their generative abilities, yet some … (see more)of this is also owed to the risks and costs associated with their use. On one front is their tendency to \textit{hallucinate} false or misleading information, limiting their reliability. On another is the increasing focus on the computational limitations associated with traditional self-attention based LLMs, which has brought about new alternatives, in particular recurrent models, meant to overcome them. Yet it remains uncommon to consider these two concerns simultaneously. Do changes in architecture exacerbate/alleviate existing concerns about hallucinations? Do they affect how and where they occur? Through an extensive evaluation, we study how these architecture-based inductive biases affect the propensity to hallucinate. While hallucination remains a general phenomenon not limited to specific architectures, the situations in which they occur and the ease with which specific types of hallucinations can be induced can significantly differ based on the model architecture. These findings highlight the need for better understanding both these problems in conjunction with each other, as well as consider how to design more universal techniques for handling hallucinations.

2024-12-31

ACL (Findings) (published)

Language Model-In-The-Loop: Data Optimal Approach to Recommend Actions in Text Games

Arjun V Sudhakar

Janarthanan Rajendran

A. Chandar

Large Language Models (LLMs) have demonstrated superior performance in language understanding benchmarks. A recent use case for LLMs involve… (see more)s training decision-making agents over textual information. The existing approach leverages LLM's linguistic priors for action candidate recommendations in text games, i.e., to operate without environment-provided actions. However, adapting LLMs to specific games/tasks requires a massive amount of annotated human gameplay. Moreover, in the existing approach, the language model was kept frozen during an agent's training process, which limits learning from in-game knowledge about the world. Hence, we explore strategies to adapt the language model for candidate recommendation with in-game transition in an online learning fashion to mitigate reliance on human-annotated gameplays, which are costly to acquire. In this paper, we propose in-game transition selection methods to adapt the LLM in the loop, reducing the dependency on using human-annotated gameplays while improving performance and convergence. Our method demonstrates a 53% relative improvement in average game score over the previous state-of-the-art model, achieving more than twice the convergence rate in a full-annotated dataset setting. Furthermore, even with only 10% of human annotation, we surpassed the 100\% state-of-the-art performance benchmark.

2024-06-19

rl-conference.cc/RLC/2024/Workshop/TAFM (published)

Towards Practical Tool Usage for Continually Learning LLMs

Mehdi Rezagholizadeh

A. Chandar

Large language models (LLMs) show an innate skill for solving language based tasks. But insights have suggested an inability to adjust for i… (see more)nformation or task-solving skills becoming outdated, as their knowledge, stored directly within their parameters, remains static in time. Tool use helps by offloading work to systems that the LLM can access through an interface, but LLMs that use them still must adapt to nonstationary environments for prolonged use, as new tools can emerge and existing tools can change. Nevertheless, tools require less specialized knowledge, therefore we hypothesize they are better suited for continual learning (CL) as they rely less on parametric memory for solving tasks and instead focus on learning when to apply pre-defined tools. To verify this, we develop a synthetic benchmark and follow this by aggregating existing NLP tasks to form a more realistic testing scenario. While we demonstrate scaling model size is not a solution, regardless of tool usage, continual learning techniques can enable tool LLMs to both adapt faster while forgetting less, highlighting their potential as continual learners.

2024-04-13

ArXiv (preprint)

Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models

Mehdi Rezagholizadeh

A. Chandar

2023-12-31

EMNLP (published)

Do Large Language Models Know How Much They Know?

Gabriele Prato

Shagun Sodhani

A. Chandar

2023-12-31

EMNLP (published)

Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models

Amirhossein Kazemnejad

Mehdi Rezagholizadeh

Sarath Chandar

While pre-trained language models (PLMs) have shown evidence of acquiring vast amounts of knowledge, it remains unclear how much of this par… (see more)ametric knowledge is actually usable in performing downstream tasks. We propose a systematic framework to measure parametric knowledge utilization in PLMs. Our framework first extracts knowledge from a PLM's parameters and subsequently constructs a downstream task around this extracted knowledge. Performance on this task thus depends exclusively on utilizing the model's possessed knowledge, avoiding confounding factors like insufficient signal. As an instantiation, we study factual knowledge of PLMs and measure utilization across 125M to 13B parameter PLMs. We observe that: (1) PLMs exhibit two gaps - in acquired vs. utilized knowledge, (2) they show limited robustness in utilizing knowledge under distribution shifts, and (3) larger models close the acquired knowledge gap but the utilized knowledge gap remains. Overall, our study provides insights into PLMs' capabilities beyond their acquired knowledge.

2023-11-30

Findings of the Association for Computational Linguistics: EMNLP 2023 (published)

Arjun Vaithilingam Sudhakar

Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games

Janarthanan Rajendran

A. Chandar

2023-11-12

ArXiv (preprint)

EpiK-Eval: Evaluation for Language Models as Epistemic Models

Gabriele Prato

Shagun Sodhani

A. Chandar

In the age of artificial intelligence, the role of large language models (LLMs) is becoming increasingly central. Despite their growing prev… (see more)alence, their capacity to consolidate knowledge from different training documents—a crucial ability in numerous applications—remains unexplored. This paper presents the first study examining the capability of LLMs to effectively combine such information within their parameter space. We introduce EpiK-Eval, a novel question-answering benchmark tailored to evaluate LLMs' proficiency in formulating a coherent and consistent knowledge representation from segmented narratives. Evaluations across various LLMs reveal significant weaknesses in this domain. We contend that these shortcomings stem from the intrinsic nature of prevailing training objectives. Consequently, we advocate for refining the approach towards knowledge consolidation, as it harbors the potential to dramatically improve their overall effectiveness and performance. The findings from this study offer insights for developing more robust and reliable LLMs. Our code and benchmark are available at https://github.com/chandar-lab/EpiK-Eval

2023-10-06

EMNLP/2023/Conference (accepted)

Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness

Abdelrahman Zayed

Goncalo Mordido

Hamid Palangi

Samira Shabanian

Sarath Chandar

Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity conc… (see more)erns. Prediction models may discover, use, or amplify spurious correlations based on gender or other protected personal characteristics, thus discriminating against marginalized groups. Mitigating gender bias has become an important research focus in natural language processing (NLP) and is an area where annotated corpora are available. Data augmentation reduces gender bias by adding counterfactual examples to the training dataset. In this work, we show that some of the examples in the augmented dataset can be not important or even harmful for fairness. We hence propose a general method for pruning both the factual and counterfactual examples to maximize the model's fairness as measured by the demographic parity, equality of opportunity, and equality of odds. The fairness achieved by our method surpasses that of data augmentation on three text classification datasets, using no more than half of the examples in the augmented dataset. Our experiments are conducted using models of varying sizes and pre-training settings.

2022-11-19

ArXiv (preprint)

Local Structure Matters Most: Perturbation Study in NLU

Louis Clouatre

Amal Zouaq

Sarath Chandar

Recent research analyzing the sensitivity of natural language understanding models to word-order perturbations has shown that neural models … (see more)are surprisingly insensitive to the order of words. In this paper, we investigate this phenomenon by developing order-altering perturbations on the order of words, subwords, and characters to analyze their effect on neural models' performance on language understanding tasks. We experiment with measuring the impact of perturbations to the local neighborhood of characters and global position of characters in the perturbed texts and observe that perturbation functions found in prior literature only affect the global ordering while the local ordering remains relatively unperturbed. We empirically show that neural models, invariant of their inductive biases, pretraining scheme, or the choice of tokenization, mostly rely on the local structure of text to build understanding and make limited use of the global structure.

2022-04-30

Findings of the Association for Computational Linguistics: ACL 2022 (published)